Relevant bibliographies by topics / La Monte / Dissertations / Theses

Dissertations / Theses on the topic 'La Monte'

To see the other types of publications on this topic, follow the link: La Monte.
Author: Grafiati
Published: 4 June 2021
Last updated: 20 February 2023

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles

Select a source type:

Consult the top 50 dissertations / theses for your research on the topic 'La Monte.'

Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.

You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.

Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.

1

Pérez-Cotapos, Ferrada Ana. "Centro de interpretación arqueológica Monte Verde, Puerto Montt." Tesis, Universidad de Chile, 2015. http://repositorio.uchile.cl/handle/2250/142439.

Full text
Abstract:
Memoria para optar al título de Arquitecto
Situado a 35km de Puerto Montt se encuentra el hallazgo arqueológico más antiguo de Chile actualmente. Con el asentamiento de Monte Verde se cuestionó una de las teorías de la población de América, desde entonces, el estrecho de Bering no sería el único acceso de los hombres a nuestro continente. Sin embargo, a pesar de la importancia que tiene este lugar, pasa desapercibido al no tener restos visibles. En los cerca de 40 años desde su descubrimiento sigue en las mismas condiciones. Con la compra de un sitio continuo al arqueológico por parte de la municipalidad, queda en evidencia la clara intención de realizar algo en el lugar. En este sitio, ubicado en la ribera del estero Chinchihuapi se plantea este proyecto. A través de un centro de interpretación se pone en valor el sitio arqueológico, el hallazgo, el lugar e incluso estero. La idea nace como una conexión al lugar del asentamiento, donde se encontraron restos de carpas de los antiguos habitantes. Los edificios se ubican dispersos bordeando el estero, este funciona como hilo conductor del proyecto. El programa se divide en seis núcleos que transportan al pasado, mostrando como era Monte Verde hace 18.500 años atrás. En estos edificios de estructura de madera y exterior de aluminio prepintado negro. Como contraposición, en las pasarelas metálicas se contempla el presente, la actualidad del sitio. A través de la interpretación se logra comprender la importancia de este hallazgo, descubriendo en el cauce del estero la historia del lugar.
APA, Harvard, Vancouver, ISO, and other styles
2

Jiménez, Parot Isabel. "Museo arqueológico de sitio Monte Verde Puerto Montt, X región, Chile." Tesis, Universidad de Chile, 2015. http://repositorio.uchile.cl/handle/2250/142784.

Full text
Abstract:
Memoria para optar al título de Arquitecto
En Monte Verde, a menos de 30 kilómetros de Puerto Montt se hallaron los restos humanos más antiguos de América, que datan de más de 12.500 años desde el presente. Fue el descubrimiento de estos vestigios arqueológicos que se derribó el Consenso de Clovis, la teoría de poblamiento de América más aceptada en aquél entonces. Este es uno de los descubrimientos más importante de los últimos años y revolucionó la comunidad científica. A pesar de la importancia de Monte Verde, la población nacional e internacional aún no tiene conocimiento del lugar ni de los hallazgos de la cultura que allí tuvo lugar. El proyecto desarrollado durante el proceso de titulación busca proponer una alternativa para el Museo Arqueológico de Sitio Monte Verde, el cual por varios motivos no se ha llevado aún a cabo. Esta propuesta emplaza el edificio en el sitio mismo de los hallazgos, el cual fue declarado Monumento Nacional, es parte de nuestro patrimonio y de nuestra identidad nacional. La condición de museo de sitio busca acercar al visitante a la labor realizada por arqueólogos y ser parte del descubrimiento de el sitio pues este no ha sido excavado completamente y se han encontrado restos en todos los pozos de sondeo realizados los últimos veranos. Esta situación no permite la intervención del terreno ni que el visitante circule por el terreno, es por ello que se propone un sistema de pasarelas elevadas del suelo que permitan al visitante observar el trabajo arqueológico además de plantear un museo de carácter fijo, en un terreno aledaño, donde se exhiban y conserven los restos arqueológicos, tanto los que actualmente están en las bodegas de la Universidad Austral de Valdivia como también aquellos que serán encontrados en el futuro. Es fundamental valorar nuestro patrimonio nacional y somos nosotros los encargados de su conservación. Cada vez se han encontrado más sitios tanto de interés histórico como también científico. El proyecto desarrollado como sistemas de pasarelas podría adaptarse a los distintos sitios arqueológicos que están en etapas investigativas, protegiéndolos del posible deterioro y apropiando estos sitios tanto a habitantes como turistas.
APA, Harvard, Vancouver, ISO, and other styles
3

Janzon, Krister. "Monte Carlo Path Simulation and the Multilevel Monte Carlo Method." Thesis, Umeå universitet, Institutionen för fysik, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-151975.

Full text
Abstract:
A standard problem in the field of computational finance is that of pricing derivative securities. This is often accomplished by estimating an expected value of a functional of a stochastic process, defined by a stochastic differential equation (SDE). In such a setting the random sampling algorithm Monte Carlo (MC) is useful, where paths of the process are sampled. However, MC in its standard form (SMC) is inherently slow. Additionally, if the analytical solution to the underlying SDE is not available, a numerical approximation of the process is necessary, adding another layer of computational complexity to the SMC algorithm. Thus, the computational cost of achieving a certain level of accuracy of the estimation using SMC may be relatively high. In this thesis we introduce and review the theory of the SMC method, with and without the need of numerical approximation for path simulation. Two numerical methods for path approximation are introduced: the Euler–Maruyama method and Milstein's method. Moreover, we also introduce and review the theory of a relatively new (2008) MC method – the multilevel Monte Carlo (MLMC) method – which is only applicable when paths are approximated. This method boldly claims that it can – under certain conditions – eradicate the additional complexity stemming from the approximation of paths. With this in mind, we wish to see whether this claim holds when pricing a European call option, where the underlying stock process is modelled by geometric Brownian motion. We also want to compare the performance of MLMC in this scenario to that of SMC, with and without path approximation. Two numerical experiments are performed. The first to determine the optimal implementation of MLMC, a static or adaptive approach. The second to illustrate the difference in performance of adaptive MLMC and SMC – depending on the used numerical method and whether the analytical solution is available. The results show that SMC is inferior to adaptive MLMC if numerical approximation of paths is needed, and that adaptive MLMC seems to meet the complexity of SMC with an analytical solution. However, while the complexity of adaptive MLMC is impressive, it cannot quite compensate for the additional cost of approximating paths, ending up roughly ten times slower than SMC with an analytical solution.
APA, Harvard, Vancouver, ISO, and other styles
4

Jun, Seong-Hwan. "Entangled Monte Carlo." Thesis, University of British Columbia, 2013. http://hdl.handle.net/2429/44953.

Full text
Abstract:
A recurrent problem in statistics is that of computing an expectation involving intractable integration. In particular, this problem arises in Bayesian statistics when computing an expectation with respect to a posterior distribution known only up to a normalizing constant. A common solution is to use Monte Carlo simulation to estimate the target expectation. Two of the most commonly adopted simulation methods are Markov Chain Monte Carlo (MCMC) and Sequential Monte Carlo (SMC) methods. However, these methods fail to scale up with the size of the inference problem. For MCMC, the problem takes the form of simulations that must be ran for a long time in order to obtain an accurate inference. For SMC, one may not be able to store enough particles to exhaustively explore the state space. We propose a novel scalable parallelization of Monte Carlo simulation, Entangled Monte Carlo simulation, that can scale up with the size of the inference problem. Instead of transmitting particles over the network, our proposed algorithm reconstructs the particles from the particle genealogy using the notion of stochastic maps borrowed from perfect simulation literature. We propose bounds on the expected time for particles to coalesce based on the coalescent model. Our empirical results also demonstrate the efficacy of our method on datasets from the field of phylogenetics.
APA, Harvard, Vancouver, ISO, and other styles
5

Lee, Kevin Stuart. "City-dwelling Samnites : urban settlement at Monte Pallano and Monte Vairano." Thesis, University of British Columbia, 2016. http://hdl.handle.net/2429/58790.

Full text
Abstract:
The ancient Samnites of south-central Italy have been cast by both ancient and modern authors as rough-and-tumble highlanders due to their habitation of the rugged river valleys of the southern Apennines and their ferocious resistance to Roman expansion in the fifth and fourth centuries B.C. The most visible remainders of Samnite civilization are the great fortresses of polygonal masonry that crown many hilltops and mountain peaks in the modern regioni of Abruzzo, Molise, and Campania, around which Samnite farms, villages, and sanctuaries coalesced. Since the publication of Edward Togo Salmon’s Samnium and the Samnites and the wide adoption of Adriano La Regina’s pagus-vicus model for Apenninic settlement, there has been a marked resistance in modern scholarship to characterizing the largest of these fortified centers as cities. This stands in stark contrast with ancient authors, in particular Livy, who frequently refer to Samnite population centers in urban terms. This thesis defends the ancient view of the Samnites as an urban people, with permanently occupied hill-forts as their cities. It begins with a close examination of Livy’s monumental history of Rome, in particular his narration of the Samnite Wars in the seventh through tenth books. This first chapter analyzes the terminology Livy employs to describe Samnite cities and their features, and reconstructs from the text a Roman understanding of the city. The second and third chapters review the archaeological evidence from two well-documented Samnite fastnesses, Monte Pallano and Monte Vairano, in light of this understanding to illustrate how the Romans could understand them as cities. These chapters further illuminate aspects of community, state formation, and spatial organization at these cities in light of Michael Mann’s IEMP theory of power relations and Roberto Camagni’s factors for urban genesis. This thesis provides an alternative interpretation of the literary and archaeological evidence that is more faithful to the former and as such provides a firmer foundation for understanding the latter.
Arts, Faculty of
Classical, Near Eastern and Religious Studies, Department of
Graduate
APA, Harvard, Vancouver, ISO, and other styles
6

Dickinson, Andrew Samuel. "On the analysis of Monte Carlo and quasi-Monte Carlo methods." Thesis, University of Oxford, 2004. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.409715.

Full text
APA, Harvard, Vancouver, ISO, and other styles
7

Göncü, Ahmet. "Monte Carlo and quasi-Monte Carlo methods in pricing financial derivatives." Tallahassee, Florida : Florida State University, 2009. http://etd.lib.fsu.edu/theses/available/etd-06232009-140439/.

Full text
Abstract:
Thesis (Ph. D.)--Florida State University, 2009.
Advisor: Giray Ökten, Florida State University, College of Arts and Sciences, Dept. of Mathematics. Title and description from dissertation home page (viewed on Oct. 5, 2009). Document formatted into pages; contains x, 105 pages. Includes bibliographical references.
APA, Harvard, Vancouver, ISO, and other styles
8

Berezovska, Ganna [Verfasser], and Alexander [Akademischer Betreuer] Blumen. "Monte Carlo study of semiflexible polymers = Monte Carlo Studie von semiflexiblen Polymeren." Freiburg : Universität, 2011. http://d-nb.info/1125885467/34.

Full text
APA, Harvard, Vancouver, ISO, and other styles
9

Drumond, Lorenzo. "Il Metodo Monte Carlo." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2020. http://amslaurea.unibo.it/20698/.

Full text
Abstract:
La tesi introduce le tecniche di approssimazione numerica note come Metodo Monte Carlo. Dopo una breve presentazione dell'apparato teorico che giustifica il funzionamento di questo metodo, si procede con uno studio sulla stima dell'errore, focalizzando l'interesse sulla dimostrazione del Teorema di Berry-Esseen. La tesi continua affrontando il tema della generazione di numeri pseudocasuali, fondamentali nel Metodo Monte Carlo, per poi finire con tre esempi di applicazione.
APA, Harvard, Vancouver, ISO, and other styles
10

Chin, Mary Pik Wai. "Monte Carlo portal dosimetry." Thesis, Cardiff University, 2005. http://orca.cf.ac.uk/54085/.

Full text
Abstract:
This project developed a solution for verifying external photon beam radiotherapy. The solution is based on a calibration chain for deriving portal dose maps from acquired portal images, and a calculation framework for predicting portal dose maps. Quantitative comparison between acquired and predicted portal dose maps accomplishes both geometric (patient positioning with respect to the beam) and dosimetric (2D fluence distribution of the beam) verifications. A disagreement would indicate that beam delivery had not been according to plan. The solution addresses the clinical need for verifying radiotherapy both pre-treatment (without patient in the beam) and on-treatment (with patient in the beam). Medical linear accelerators mounted with electronic portal imaging devices (EPIDs) were used to acquire portal images. Two types of EPIDs were investigated: the amorphous silicon (a-Si) and the scanning liquid ion chamber (SLIC). The EGSnrc family of Monte Carlo codes were used to predict portal dose maps by computer simulation of radiation transport in the beam-phantom-EPID configuration. Monte Carlo simulations have been implemented on several levels of High Throughput Computing (HTC), including the Grid, to reduce computation time. The solution has been tested across the entire clinical range of gantry angle, beam size (5 cm x 5 cm to 20 cm x 20 cm), beam-patient and patient-EPID separations (4 cm to 38 cm). In these tests of known beam-phantom-EPID configurations, agreement between acquired and predicted portal dose profiles was consistently within 2% of the central axis value. This Monte Carlo portal dosimetry solution therefore achieved combined versatility, accuracy and speed not readily achievable by other techniques.
APA, Harvard, Vancouver, ISO, and other styles
11

Azevedo, Maria Leonor de Amaral Marques e. Fraüsto de. "Caso Monte dos Coutos." Master's thesis, Universidade de Lisboa. Faculdade de Arquitetura, 2016. http://hdl.handle.net/10400.5/12574.

Full text
APA, Harvard, Vancouver, ISO, and other styles
12

McNeil-Watson, Graham. "Phase switch Monte Carlo." Thesis, University of Bath, 2007. https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.486842.

Full text
Abstract:
Computational studies of phase behaviour have always proved difficult, since phase . transitions are inherently slow processes compared to accessible simulation timescales. Despite valiant efforts by researchers there remains a dearth of efficient, robust and scalable methods for determining phase equilibria,· especially in the case of fluid-crystalline solid transitions. This thesis is about such phase coexistence problems, the existing solutions, and more advanced methods that have only recently come into their own. ... Extended sampling methods are examined in detail, and applied to a testbed system, the critical point Lennard-Jones fluid, leading to an estimate of the system free energy in the thermodynamic limit. Then a comparatively new technique, phase switch Monte Carlo (Phys. Rev. Lett. 85, 5138) is applied initially to the venerable hard sphere system. The method overcomes many of the shortcomings present in other works by directly connecting the coexisting phases in a single simulation, and doing so without creating an artificial inter-phase route but rather affecting a direct 'phase leap' from one phase to the other. Finally, phase switch is generalised to soft potentials and applied to the Lennard-Jones freezing transition, resulting in an extensive mapping of the phase boundary for a variety of system sizes (J. Chern. Phys 124, 064504).
APA, Harvard, Vancouver, ISO, and other styles
13

Ahlert, Martina. "Mulheres de Monte Verde." Florianópolis, SC, 2008. http://repositorio.ufsc.br/xmlui/handle/123456789/91731.

Full text
Abstract:
Dissertação (mestrado) - Universidade Federal de Santa Catarina, Centro de Filosofia e Ciências Humanas. Programa de Pós-Graduação em Antropologia Social.
Made available in DSpace on 2012-10-24T01:57:09Z (GMT). No. of bitstreams: 1 251560.pdf: 731841 bytes, checksum: 4964a7450c0dac38c7834b2db23acbc3 (MD5)
Este trabalho se constitui como uma análise de um núcleo do Programa Fome Zero, do governo federal, na cidade de Porto Alegre (RS). A pesquisa se desenvolveu no período de dezembro de 2004 até junho de 2007. Os dados apresentados surgiram a partir da realização de uma etnografia junto a um grupo de mulheres, conhecidas como coordenadoras do Núcleo Monte Verde do Programa Fome Zero. Localizado em um loteamento popular da cidade de Porto Alegre, o Núcleo tinha como proposta realizar, naquele espaço, a distribuição das cestas básicas provenientes de doações da sociedade civil, assim como propor iniciativas de geração de trabalho e renda. Duas categorias se apresentaram como fundamentais na análise das atividades realizadas pelo Núcleo: gênero e classe. Neste sentido, o trabalho do Núcleo estava marcado por traços considerados femininos naquele grupo popular, como a importância da maternidade e do parentesco, uma forma de inserção no mercado de trabalho e uma rotina basicamente doméstica e local. O envolvimento das mulheres com a atividade de coordenação do Núcleo tinha relação com aprendizados variados sobre a busca de recursos - monetários ou não - para suas casas. Os programas governamentais e envolvimento com as políticas sociais eram, especialmente, contribuições femininas no espaço familiar. A dissertação ainda realiza apontamentos sobre a relação que as coordenadoras desempenhavam com o ambiente da política institucional e o espaço do Loteamento. Acompanhando a trajetória do Núcleo Monte Verde, pode-se ver como se deu o processo de profissionalização dos trabalhos desempenhados no local, assim como a saída das coordenadoras desta atividade. Esta perspectiva possibilitou perceber de que maneira os períodos políticos dirigidos pelos processos eleitorais e as mudanças partidárias influem sobre os beneficiários e participantes dos programas governamentais. Apesar da presença importante do Estado na vida das coordenadoras, assim como dos coordenadores de outros núcleos da cidade, normalmente sua participação no Programa Fome Zero não era associada à política, mas à possibilidade "da ajuda". Percebendo os sentidos múltiplos dados ao envolvimento no programa governamental, também se pode observar as assimetrias entre as propostas políticas provenientes dos setores governamentais e sua vivência pelo público ao qual se destinam.
APA, Harvard, Vancouver, ISO, and other styles
14

Bakra, Eleni. "Aspects of population Markov chain Monte Carlo and reversible jump Markov chain Monte Carlo." Thesis, University of Glasgow, 2009. http://theses.gla.ac.uk/1247/.

Full text
APA, Harvard, Vancouver, ISO, and other styles
15

Bryskhe, Henrik. "Optimization of Monte Carlo simulations." Thesis, Uppsala University, Department of Information Technology, 2009. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-121843.

Full text
Abstract:

This thesis considers several different techniques for optimizing Monte Carlo simulations. The Monte Carlo system used is Penelope but most of the techniques are applicable to other systems. The two mayor techniques are the usage of the graphics card to do geometry calculations, and raytracing. Using graphics card provides a very efficient way to do fast ray and triangle intersections. Raytracing provides an approximation of Monte Carlo simulation but is much faster to perform. A program was also written in order to have a platform for Monte Carlo simulations where the different techniques were implemented and tested. The program also provides an overview of the simulation setup, were the user can easily verify that everything has been setup correctly. The thesis also covers an attempt to rewrite Penelope from FORTAN to C. The new version is significantly faster and can be used on more systems. A distribution package was also added to the new Penelope version. Since Monte Carlo simulations are easily distributed, running this type of simulations on ten computers yields ten times the speedup. Combining the different techniques in the platform provides an easy to use and at the same time efficient way of performing Monte Carlo simulations.

APA, Harvard, Vancouver, ISO, and other styles
16

Zeineh, Rami. "Adaptive threshold Monte Carlo localization." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 2001. http://www.collectionscanada.ca/obj/s4/f2/dsk3/ftp04/MQ61962.pdf.

Full text
APA, Harvard, Vancouver, ISO, and other styles
17

Holenstein, Roman. "Particle Markov chain Monte Carlo." Thesis, University of British Columbia, 2009. http://hdl.handle.net/2429/7319.

Full text
Abstract:
Markov chain Monte Carlo (MCMC) and sequential Monte Carlo (SMC) methods have emerged as the two main tools to sample from high-dimensional probability distributions. Although asymptotic convergence of MCMC algorithms is ensured under weak assumptions, the performance of these latters is unreliable when the proposal distributions used to explore the space are poorly chosen and/or if highly correlated variables are updated independently. In this thesis we propose a new Monte Carlo framework in which we build efficient high-dimensional proposal distributions using SMC methods. This allows us to design effective MCMC algorithms in complex scenarios where standard strategies fail. We demonstrate these algorithms on a number of example problems, including simulated tempering, nonlinear non-Gaussian state-space model, and protein folding.
APA, Harvard, Vancouver, ISO, and other styles
18

Byrd, Jonathan Michael Robert. "Parallel Markov Chain Monte Carlo." Thesis, University of Warwick, 2010. http://wrap.warwick.ac.uk/3634/.

Full text
Abstract:
The increasing availability of multi-core and multi-processor architectures provides new opportunities for improving the performance of many computer simulations. Markov Chain Monte Carlo (MCMC) simulations are widely used for approximate counting problems, Bayesian inference and as a means for estimating very highdimensional integrals. As such MCMC has found a wide variety of applications in fields including computational biology and physics,financial econometrics, machine learning and image processing. This thesis presents a number of new method for reducing the runtime of Markov Chain Monte Carlo simulations by using SMP machines and/or clusters. Two of the methods speculatively perform iterations in parallel, reducing the runtime of MCMC programs whilst producing statistically identical results to conventional sequential implementations. The other methods apply only to problem domains that can be presented as an image, and involve using various means of dividing the image into subimages that can be proceed with some degree of independence. Where possible the thesis includes a theoretical analysis of the reduction in runtime that may be achieved using our technique under perfect conditions, and in all cases the methods are tested and compared on selection of multi-core and multi-processor architectures. A framework is provided to allow easy construction of MCMC application that implement these parallelisation methods.
APA, Harvard, Vancouver, ISO, and other styles
19

Lewis, R. D. "Monte Carlo modelling for radiotherapy." Thesis, Swansea University, 2000. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.637892.

Full text
Abstract:
The Monte Carlo code MCNP-4B has been utilised to investigate the origins of radiation dose perturbation in the head and neck region, arising from natural heterogeneities, the changing external contours of the patient, boundaries between materials of different atomic number and prosthetic implants. MCNP-4B was used to develop a simple model of a linear accelerator treatment head which incorporated the electron target, primary collimator, beam flattening filter and the secondary collimators. The model was used to calculate the energy spectra and angular distribution of the x-ray beam from a 4 MV Philips SL 75/5 and a 10 MV SL 15, and then tested by using these data to compute the central and off-axis x-ray beam profiles for various field sizes in water. Monte Carlo simulations using the calculated spectra were used to assess the dose distribution of treatment plans obtained in a simple heterogeneous phantom by several commercially available treatment planning systems. Practical measurements were undertaken using film dosimetry. The dose distributions were calculated for a variety of irradiation conditions designed to show the effects of surface obliquity, inhomogeneities and missing tissue above tangential beams. The results show maximum differences of 47% between some planning algorithm and film. Overall, the dose distribution obtained from film was most faithfully reproduced by the MCNP. The dose due to backscatter and lack of forward scatter from a metal implant within a head and neck phantom has been shown vary with atomic number, field size, surface obliquity, implant thickness, variations in secondary electron transport and the presence of teeth.
APA, Harvard, Vancouver, ISO, and other styles
20

Taft, Keith. "Monte Carlo methods for radiosity." Thesis, University of Liverpool, 2002. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.272796.

Full text
APA, Harvard, Vancouver, ISO, and other styles
21

Whiteley, Nicholas Paul. "Advances in Monte Carlo filtering." Thesis, University of Cambridge, 2009. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.611476.

Full text
APA, Harvard, Vancouver, ISO, and other styles
22

Badinski, Alexander Nikolai. "Forces in quantum Monte Carlo." Thesis, University of Cambridge, 2008. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.612494.

Full text
APA, Harvard, Vancouver, ISO, and other styles
23

Strathmann, Heiko. "Kernel methods for Monte Carlo." Thesis, University College London (University of London), 2018. http://discovery.ucl.ac.uk/10040707/.

Full text
Abstract:
This thesis investigates the use of reproducing kernel Hilbert spaces (RKHS) in the context of Monte Carlo algorithms. The work proceeds in three main themes. Adaptive Monte Carlo proposals: We introduce and study two adaptive Markov chain Monte Carlo (MCMC) algorithms to sample from target distributions with non-linear support and intractable gradients. Our algorithms, generalisations of random walk Metropolis and Hamiltonian Monte Carlo, adaptively learn local covariance and gradient structure respectively, by modelling past samples in an RKHS. We further show how to embed these methods into the sequential Monte Carlo framework. Efficient and principled score estimation: We propose methods for fitting an RKHS exponential family model that work by fitting the gradient of the log density, the score, thus avoiding the need to compute a normalization constant. While the problem is of general interest, here we focus on its embedding into the adaptive MCMC context from above. We improve the computational efficiency of an earlier solution with two novel fast approximation schemes without guarantees, and a low-rank, Nyström-like solution. The latter retains the consistency and convergence rates of the exact solution, at lower computational cost. Goodness-of-fit testing: We propose a non-parametric statistical test for goodness-of-fit. The measure is a divergence constructed via Stein's method using functions from an RKHS. We derive a statistical test, both for i.i.d. and non-i.i.d. samples, and apply the test to quantifying convergence of approximate MCMC methods, statistical model criticism, and evaluating accuracy in non-parametric score estimation.
APA, Harvard, Vancouver, ISO, and other styles
24

Silva, Ivair Ramos. "Otimalidade de Testes Monte Carlo." Universidade Federal de Minas Gerais, 2011. http://hdl.handle.net/1843/ICED-8H2HFS.

Full text
Abstract:
A operacionalização de um teste de hipóteses é condicionada ao conhecimento da distribuição de probabilidade da estatística de teste sob a hipótese nula H0. Caso não se conheça a distribuição da estatística de teste sob H0, sua distribuição assintótica pode ser usada para que a decisão sobre a rejeição ou não de H0 possa ser feita, o que exige o estudo dos tamanhos amostrais para os quais tal distribuição assintótica se verifica. Quando a distribuição assintótica também não pode ser deduzida analiticamente, métodos de reamostragem podem ser aplicados para a construção de um critério alternativo de decisão, tais como reamostragem Bootstrap, testes de permutação e simulação Monte Carlo (MC), sendo este último o objeto de estudo deste trabalho. Os testes de hipóteses montados pela utilização de simulações Monte Carlo podem ser divididos em dois tipos: os que se baseiam em um número m fixo de simulações, que é a estratégia convencional; e os procedimentos sequenciais, com os quais o número de simulações a serem geradas não é previamente fxado. Apesar de atualmente contarmos com recursos computacionais que favorecem o processamento de grandes bases de dados de forma extremamente veloz, ainda existem situações em que o tempo de processamento de uma estatística de teste é longo, o que motiva o desenvolvimento e utilização dos procedimentos sequenciais. Os aspectos que recebem forte atenção na literatura sobre testes MC são: a busca por procedimentos que apresentem reduzido tempo médio de simulação até que a decisão sobre H0 seja efetuada; a estipulação de cotas para a probabilidade da decisão quanto à rejeição de H0 ser diferente da que se tomaria com o teste exato (risco de reamostragem); a estimação do valor-p; e a estipulação de cotas para as possíveis perdas de poder do teste MC sequencial em relação ao teste MC convencional ou em relação ao respectivo teste exato. Usando certas suposições sobre a distribuição de probabilidade e a função poder associadas à estatística de teste, a literatura mostra que o poder do teste MC convencional é praticamente igual ao poder do teste exato. Um dos objetivos desta tese é demonstrar que é possível obter cotas para a diferença de poder entre o teste MC convencional e o teste exato que valem para qualquer estatística de teste, ou seja, a validade de tais cotas não depende de suposições além das necessárias à existência de um teste exato. Besag and Clifford (1991) propuseram um procedimento de teste MC sequencial que, sob H0, apresenta baixo tempo de execução. bjetivamos mostrar aqui como deve ser feita a escolha dos parâmetros de operacionalização deste procedimento sequencial. Primeiramente, mostramos como otimizar a escolha do número máximo de simulações sem afetar seu poder e, em seguida, demonstramos a forma de aplicar a regra de interrupção das simulações de modo a garantir um mesmo poder que o teste convencional. O procedimento sequencial de Besag and Clifford (1991) só apresenta redução no tempo de execução nos casos em que H0 é verdadeira. Com a principal finalidade de tornar o teste MC sequencial mais veloz que o MC convencional também quando a hipótese nula é falsa, procedimentos sequenciais alternativos tem sido propostos na literatura. O cálculo analítico exato do poder de tais procedimentos sequenciais, bem como do valor esperado do número de simulações, são intratáveis para o caso geral, pois envolve o conhecimento da distribuição de probabilidade do valor-p, que por sua vez depende de cada aplicação específica. Pelo uso de algumas restrições ao comportamento da distribuição de probabilidade do valor-p, alguns autores obtiveram cotas para o risco de reamostragem e para a esperança do número de simulações para procedimentos sequenciais para os quais, em cada tempo t de simulação, a regra de iinterrupção das simulações é dada por uma função linear em t. Nesta tese, construimos um procedimento sequencial que permite um formato geral para a regra de interrupção das simulações, o qual chamaremos de teste MC sequencial generalizado. Esta construção absorve as principais propostas apresentadas na literatura e permite um tratamento analítico do poder e do número esperado de simulações para uma estatística de teste qualquer. Isto é feito pela elaboração de cotas superiores para a perda de poder e para a esperança do número de simulações. Com base em conceitos desenvolvidos nesta tese, apresentamos a construção do procedimento ótimo em termos do número esperado de simulações. Nós também cotamos o risco de reamostragem dentro de uma extensa classe de distribuições de probabilidade para o valor-p.
APA, Harvard, Vancouver, ISO, and other styles
25

Lin, Xichen. "Monte Carlo Simulation and Integration." Scholarship @ Claremont, 2018. https://scholarship.claremont.edu/cmc_theses/2009.

Full text
Abstract:
In this paper, we introduce the Tootsie Pop Algorithm and explore its use in different contexts. It can be used to estimate more general problems where a measure is defined, or in the context of statistics application, integration involving high dimensions. The Tootsie Pop Algorithm was introduced by Huber and Schott[2] The general process of Tootsie Pop Algorithm, just like what its name suggests, is a process of peeling down the outer shell, which is the larger enclosing set, to the center, which is the smaller enclosed. We obtain the average number of peels, which gives us an understanding of the ratio between the size of the shell and the size of the center. Each peel is generated by a random draw within the outer shell: if the drawn point is located in the center, we are done, else we update the outer shell such that the drawn point is right on its edge.
APA, Harvard, Vancouver, ISO, and other styles
26

Tuffin, Bruno. "Simulation acceleree par les methodes de monte carlo et quasi-monte carlo : theorie et applications." Rennes 1, 1997. http://www.theses.fr/1997REN10181.

Full text
Abstract:
Dans cette these nous etudions et appliquons les methodes de monte carlo et quasi-monte carlo. Nous nous interessons premierement a la theorie. Les methodes de quasi-monte carlo sont basees sur deux notions : la variation et la discrepance. Comme premiere contribution, nous ameliorons la repartition d'une famille importante de suites a discrepance faible, les suites de halton. Nous realisons ensuite une technique analogue a la reduction de la variance dans les methodes de monte carlo, la reduction de la variation. La borne de l'erreur n'etant que rarement utilisable en pratique, nous proposons une approche pour l'utilisation des suites a discrepance faible comme technique de reduction de la variance dans les methodes de monte carlo. Nous analysons l'efficacite de cette reduction et comparons les differentes suites afin de choisir la mieux adaptee. La deuxieme partie de la these est consacree a des applications concretes et efficaces de ces methodes. Nous considerons d'abord les reseaux de files d'attente multi-classes a forme produit et ameliorons leur simulation par deux techniques differentes de reduction de la variance : les variables antagonistes et les suites a discrepance faible. Cette derniere methode est ensuite appliquee a la simulation d'un systeme cellulaire avec partage dynamique des ressources. Finalement, nous etudions la simulation des systemes markoviens hautement fiables et approfondissons les methodes existantes. Nous introduisons un nouveau concept, l'approximation normale bornee, qui permet d'obtenir une approximation de la loi normale satisfaisante dans le theoreme de la limite centrale, quelle que soit la fiabilite du systeme etudie, et donnons une condition necessaire et suffisante sur la mesure d'echantillonnage preferentiel pour obtenir cette propriete.
APA, Harvard, Vancouver, ISO, and other styles
27

Hoffmann, Jochen. "Monte-Carlo- und Pfad-Integral-Monte-Carlo-Simulationen zu Strukturen und Phasenübergängen in Nano-Porenkondensaten." [S.l. : s.n.], 2002. http://www.bsz-bw.de/cgi-bin/xvms.cgi?SWB9910270.

Full text
APA, Harvard, Vancouver, ISO, and other styles
28

Ounaissi, Daoud. "Méthodes quasi-Monte Carlo et Monte Carlo : application aux calculs des estimateurs Lasso et Lasso bayésien." Thesis, Lille 1, 2016. http://www.theses.fr/2016LIL10043/document.

Full text
Abstract:
La thèse contient 6 chapitres. Le premier chapitre contient une introduction à la régression linéaire et aux problèmes Lasso et Lasso bayésien. Le chapitre 2 rappelle les algorithmes d’optimisation convexe et présente l’algorithme FISTA pour calculer l’estimateur Lasso. La statistique de la convergence de cet algorithme est aussi donnée dans ce chapitre en utilisant l’entropie et l’estimateur de Pitman-Yor. Le chapitre 3 est consacré à la comparaison des méthodes quasi-Monte Carlo et Monte Carlo dans les calculs numériques du Lasso bayésien. Il sort de cette comparaison que les points de Hammersely donne les meilleurs résultats. Le chapitre 4 donne une interprétation géométrique de la fonction de partition du Lasso bayésien et l’exprime en fonction de la fonction Gamma incomplète. Ceci nous a permis de donner un critère de convergence pour l’algorithme de Metropolis Hastings. Le chapitre 5 présente l’estimateur bayésien comme la loi limite d’une équation différentielle stochastique multivariée. Ceci nous a permis de calculer le Lasso bayésien en utilisant les schémas numériques semi implicite et explicite d’Euler et les méthodes de Monte Carlo, Monte Carlo à plusieurs couches (MLMC) et l’algorithme de Metropolis Hastings. La comparaison des coûts de calcul montre que le couple (schéma semi-implicite d’Euler, MLMC) gagne contre les autres couples (schéma, méthode). Finalement dans le chapitre 6 nous avons trouvé la vitesse de convergence du Lasso bayésien vers le Lasso lorsque le rapport signal/bruit est constant et le bruit tend vers 0. Ceci nous a permis de donner de nouveaux critères pour la convergence de l’algorithme de Metropolis Hastings
The thesis contains 6 chapters. The first chapter contains an introduction to linear regression, the Lasso and the Bayesian Lasso problems. Chapter 2 recalls the convex optimization algorithms and presents the Fista algorithm for calculating the Lasso estimator. The properties of the convergence of this algorithm is also given in this chapter using the entropy estimator and Pitman-Yor estimator. Chapter 3 is devoted to comparison of Monte Carlo and quasi-Monte Carlo methods in numerical calculations of Bayesian Lasso. It comes out of this comparison that the Hammersely points give the best results. Chapter 4 gives a geometric interpretation of the partition function of the Bayesian lasso expressed as a function of the incomplete Gamma function. This allowed us to give a convergence criterion for the Metropolis Hastings algorithm. Chapter 5 presents the Bayesian estimator as the law limit a multivariate stochastic differential equation. This allowed us to calculate the Bayesian Lasso using numerical schemes semi-implicit and explicit Euler and methods of Monte Carlo, Monte Carlo multilevel (MLMC) and Metropolis Hastings algorithm. Comparing the calculation costs shows the couple (semi-implicit Euler scheme, MLMC) wins against the other couples (scheme method). Finally in chapter 6 we found the Lasso convergence rate of the Bayesian Lasso when the signal / noise ratio is constant and when the noise tends to 0. This allowed us to provide a new criteria for the convergence of the Metropolis algorithm Hastings
APA, Harvard, Vancouver, ISO, and other styles
29

Mandreoli, Lorenzo. "Density based Kinetic Monte Carlo Methods." [S.l.] : [s.n.], 2005. http://deposit.ddb.de/cgi-bin/dokserv?idn=975329111.

Full text
APA, Harvard, Vancouver, ISO, and other styles
30

Brangian, Claudio. "Monte Carlo simulations of Potts glasses." [S.l.] : [s.n.], 2002. http://ArchiMeD.uni-mainz.de/pub/2002/0115/diss.pdf.

Full text
APA, Harvard, Vancouver, ISO, and other styles
31

Radev, Rossen. "Monte Carlo Group - Atomic Physics Department." Phd thesis, Monte Carlo Group, Atomic Physics Department, University of Sofia, 1997. http://cluster.phys.uni-sofia.bg:8080/.

Full text
APA, Harvard, Vancouver, ISO, and other styles
32

Sebastian, Shalin. "Empirical evaluation of Monte Carlo sampling /." Available to subscribers only, 2005. http://proquest.umi.com/pqdweb?did=1075709431&sid=9&Fmt=2&clientId=1509&RQT=309&VName=PQD.

Full text
APA, Harvard, Vancouver, ISO, and other styles
33

Schyberg, Oskar. "Monte Carlo Study of Reinsurance Contracts." Licentiate thesis, Mälardalens högskola, Akademin för utbildning, kultur och kommunikation, 2013. http://urn.kb.se/resolve?urn=urn:nbn:se:mdh:diva-18374.

Full text
Abstract:
This thesis is based on three articles concerning to experimental softwarefor evaluation of reinsurance contracts. In paper A we describe and usethe reinsurance analyser (ReAn), an open-source software for analysis ofreinsurance contacts. Moreover, we discuss experimental results, especiallythe risk comparison of excess-of-loss and largest claims reinsurance treaties.In paper B we expand the software including a new excess-of-loss treaty withupper limit. We perform experimental studies comparing extreme value andexcess-of-loss reinsurance treaties. In paper C, we perform a more in depthpresentation of the software. We introduce new treaties as combinations ofstandard treaties. Experimental comparisons are made between these treatiesand other extreme value treaties.
APA, Harvard, Vancouver, ISO, and other styles
34

Hine, Nicholas. "New applications of quantum Monte Carlo." Thesis, Imperial College London, 2007. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.446023.

Full text
APA, Harvard, Vancouver, ISO, and other styles
35

Zhang, Kai. "Monte Carlo methods in derivative modelling." Thesis, University of Warwick, 2011. http://wrap.warwick.ac.uk/35689/.

Full text
Abstract:
This thesis addresses issues in discretization and variance reduction methods for Monte Carlo simulation. For the discretization methods, we investigate the convergence properties of various Itˆo-Taylor schemes and the strong Taylor expansion (Siopacha and Teichmann [77]) for the LIBOR market model. We also provide an improvement on the strong Taylor expansion method which produces lower pricing bias. For the variance reduction methods, we have four contributions. Firstly, we formulate a general stochastic volatility model nesting many existing models in the literature. Secondly, we construct a correlation control variate for this model. Thirdly, we apply the model as well as the new control variate to pricing average rate and barrier options. Numerical results demonstrate the improvement over using old control variates alone. Last but not least, with the help of our model and control variate, we explore the variations in barrier option pricing consistent with the implied volatility surface.
APA, Harvard, Vancouver, ISO, and other styles
36

Maggio, Emilio. "Monte Carlo methods for visual tracking." Thesis, Queen Mary, University of London, 2008. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.497791.

Full text
APA, Harvard, Vancouver, ISO, and other styles
37

Lee, Ming Ripman, and 李明. "Monte Carlo simulation for confined electrolytes." Thesis, The University of Hong Kong (Pokfulam, Hong Kong), 2000. http://hub.hku.hk/bib/B31240513.

Full text
APA, Harvard, Vancouver, ISO, and other styles
38

Phillips, Richard J. "Monte Carlo generation of Cerenkov radiation." Thesis, Monterey, California. Naval Postgraduate School, 1989. http://hdl.handle.net/10945/26090.

Full text
APA, Harvard, Vancouver, ISO, and other styles
39

Anderson, Jeppe Rosenkrantz. "Monte Carlo studies of BFKL physics." Thesis, Durham University, 2002. http://etheses.dur.ac.uk/4118/.

Full text
Abstract:
We study the properties of the BFKL evolution of a (-channel gluon exchange in the high-energy limit. In particular we formulate a solution to the BFKL evolution equation in terms of an explicit sum over emitted gluons, which allows for a Monte Carlo integration of the resulting rapidity ordered multi-gluon phase space. This formulation allows for an introduction of the running of the coupling to the BFKL evolution. More importantly, the Monte Carlo implementation of the solution to the BFKL evolution equation allows for studies of the exclusive final states resulting from the exchange. The full control over the gluon radiation allows for energy and momentum conservation to be observed when calculating the hadronic cross sections. This is in contrast to the standard analytic approach to BFKL physics, which solves the BFKL equation by effectively summing over any number of gluons emitted and integrating over the full rapidity ordered allowed phase space. It is therefore impossible to reconstruct the parton momentum fractions exactly, and thus energy and longitudinal momentum conservation is violated. Although the effect is indeed formally subleading, we show that the numerical impact at present and planned collider energies is very significant. The reduction in parton flux due to the increased energy consumption by the BFKL evolution is sufficient to change the parton level result of an exponential rise of the dijet cross section as a function of the rapidity separation of the leading dijets to a situation much like the LO case. However, we identify the azimuthal correlation between the dijets as an observable sensitive to BFKL effects but more stable under the observation of energy and momentum conservation. We also apply the BFKL MC to a study of dijets at the Tevatron. Finally we consider W + 2-jet production, a process which in the limit of large rapidity separation between the two jets exhibit the same factorisation into two impact factors and a (-channel gluon exchange as dijet production. We identify observables in this setup, for which BFKL effects could be important.
APA, Harvard, Vancouver, ISO, and other styles
40

Crosby, Richard S. "Monte Carlo methods for lattice fields." Thesis, Massachusetts Institute of Technology, 1989. http://hdl.handle.net/1721.1/77699.

Full text
APA, Harvard, Vancouver, ISO, and other styles
41

Wang, Junxiong. "Option Pricing Using Monte Carlo Methods." Digital WPI, 2011. https://digitalcommons.wpi.edu/etd-theses/331.

Full text
Abstract:
This project is devoted primarily to the use of Monte Carlo methods to simulate stock prices in order to price European call options using control variates, and to the use of the binominal model to price American put options. At the end, we can use the information to form a portfolio position using an Interactive Brokers paper trading account. This project was done as a part of the masters capstone course Math 573: Computational Methods of Financial Mathematics.
APA, Harvard, Vancouver, ISO, and other styles
42

Lu, Mengliu. "Option Pricing Using Monte Carlo Methods." Digital WPI, 2011. https://digitalcommons.wpi.edu/etd-theses/380.

Full text
Abstract:
This paper aims to use Monte Carlo methods to price American call options on equities using the variance reduction technique of control variates and to price American put options using the binomial model. We use this information to form option positions. This project was done a part of the masters capstone course Math 573: Computational Methods of Financial Mathematics.
APA, Harvard, Vancouver, ISO, and other styles
43

Swetnam, Adam D. "Monte Carlo simulation of lattice polymers." Thesis, University of Warwick, 2011. http://wrap.warwick.ac.uk/49196/.

Full text
Abstract:
The phase behaviour of lattice polymers and peptides, under various conditions, is investigated using Monte Carlo simulation. Wang-Landau sampling is used so that, in principle, phase diagrams can be determined from a single simulation. It is demonstrated that the pseudophase diagram for polymer molecules, in several environments, can be plotted when sampling only from the internal degrees of freedom, by determining an appropriate density of states. Several improvements to the simulation methods used are detailed. A new prescription for setting the modification factor in the Wang-Landau algorithm is described, tested and found, for homopolymers, to result in near optimum convergence throughout the simulation. Different methods of selecting moves from the pull move set are detailed, and their relative efficiencies determined. Finally, it is shown that results for a polymer in a slit with one attractive surface can be determined by sampling only from the internal degrees of freedom of a lattice polymer. Adsorption of lattice polymers and peptides is investigated by determining pseudophase diagrams for individual molecules. The phase diagram for a homopolymer molecule, near a surface with a pattern of interaction, is determined, with a pseudophase identified where the polymer is commensurate with the pattern. For an example lattice peptide, the existence of the new pseudophase is found to depend on whether both hydrophobic and polar beads are attracted to the surface. The phase diagram for a ring polymer under applied force, with variable solvent quality, is determined for the first time. The effect, on the phase diagram, of topological knots in the ring polymer is investigated. In addition to eliminating pseudophases where the polymer is flattened into a single layer, it is found that non-trivial knots result in additional pseudophases for tensile force.
APA, Harvard, Vancouver, ISO, and other styles
44

Clark, Michael A. "The rational hybrid Monte Carlo algorithm." Thesis, University of Edinburgh, 2005. http://hdl.handle.net/1842/13416.

Full text
Abstract:
This thesis is concerned with the problem of generating gauge configurations for use with Monte Carlo lattice QCD calculations that include the effect of dynamical fermions. Although such effects have been included in calculations for a long time, historically it has been difficult to include the effect of the strange quark because of the square root of the Dirac operator that appears in the action. The lattice formulation of QCD is discussed, and the various fermion formulations are highlighted. Current popular algorithms used to generate gauge configurations are described, in particular the advantages and disadvantages of each are discussed. The Rational Hybrid Monte Carlo algorithm (RHMC) is introduced, this uses rational functions to approximate the matrix square root and is an exact algorithm. RHMC is compared with the Polynomial Hybrid Monte Carlo algorithm and the inexact R algorithm for two flavour staggered fermion calculations. The algorithm is found to reproduce published data and to be more efficient than the Polynomial Hybrid Monte Carlo algorithm. With the introduction of multiple time scales for the gauge and fermion parts of the action the efficiency further increases. As a means to accelerate the Monte Carlo acceptance rate of lattice QCD calculations, the splitting of the fermion determination into nth root contributions is described. This is shown to improve the conservation of the Hamiltonian. As the quark mass is decreased this is found to decrease the overall cost of calculation by allowing an increase in the integrating stepsize. An efficient formulation for applying RHMC to ASQTAD calculations is described, and it is found to be no more expensive than using the conventional R algorithm formulation. Full 2+1 quark flavour QCD calculations are undertaken using the domain wall fermion formulation. Results are generated using both RHMC and the R algorithm and comparisons are made on the basis of algorithm efficiency and hadronic observables. With the exception of the stepsize errors present in the R algorithm data, consistency is found between the two algorithms. RHMC is found to allow a much greater integrating stepsize than the R algorithm.
APA, Harvard, Vancouver, ISO, and other styles
45

Xia, Yuan. "Multilevel Monte Carlo for jump processes." Thesis, University of Oxford, 2013. http://ora.ox.ac.uk/objects/uuid:7bc8e98a-0216-4551-a1f3-1b318e514ee8.

Full text
Abstract:
This thesis consists of two parts. The first part (Chapters 2-4) considers multilevel Monte Carlo for option pricing in finite activity jump-diffusion models. We use a jump-adapted Milstein discretisation for constant rate cases and with the thinning method for bounded state-dependent rate cases. Multilevel Monte Carlo estimators are constructed for Asian, lookback, barrier and digital options. The computational efficiency is numerically demonstrated and analytically justified. The second part (Chapter 5) deals with option pricing problems in exponential Lévy models where the increments of the underlying process can be directly simulated. We discuss several examples: Variance Gamma, Normal Inverse Gaussian and alpha-stable processes and present numerical experiments of multilevel Monte Carlo for Asian, lookback, barrier options, where the running maximum of the Lévy process involved in lookback and barrier payoffs is approximated using discretely monitored maximum. To analytically verify the computational complexity of multilevel method, we also prove some upper bounds on Lp convergence rate of discretely monitored error for a broad class of Lévy processes.
APA, Harvard, Vancouver, ISO, and other styles
46

Poole, Thomas. "Calculating derivatives within quantum Monte Carlo." Thesis, Imperial College London, 2014. http://hdl.handle.net/10044/1/29359.

Full text
Abstract:
Quantum Monte Carlo (QMC) methods are powerful, stochastic techniques for computing the properties of interacting electrons and nuclei with an accuracy comparable to the standard post-Hartree--Fock methods of quantum chemistry. Whilst the favourable scaling of QMC methods enables a quantum, many-body treatment of much larger systems, the lack of accurate and efficient total energy derivatives, required to compute atomic forces, has hindered their widespread adoption. The work contained within this thesis provides an efficient procedure for calculating exact derivatives of QMC results. This procedure uses the programming technique of algorithmic differentiation (AD), which allows access to the derivatives of a computed function by applying chain rule differentiation to the underlying source code. However, this thesis shows that a straightforward differentiation of a stochastic function fails to capture the important contribution to the derivative from probabilistic decisions. A general approach for calculating the derivatives of a stochastic function is presented, where a similar adaptation of AD applied to the diffusion Monte Carlo (DMC) algorithm yields exact DMC atomic forces. The approach is validated by performing the largest ever DMC force calculations, which demonstrate the feasibility of treating systems containing thousands of electrons. The efficiency of AD also enables molecular dynamics simulations driven entirely by DMC, adding new functionality to the QMC toolkit. Another focus of this thesis is using the phenomenon of stochastic coherence to correlate DMC simulations, allowing finite difference derivatives to be obtained with a small error. Whilst this method is far easier to implement than AD, preliminary results show an instability when treating larger systems. A different approach is obtained from extrapolating this method to a finite difference step size of zero, producing algebraic expressions for a direct differentiation of the DMC algorithm.
APA, Harvard, Vancouver, ISO, and other styles
47

Zhang, Yichuan. "Scalable geometric Markov chain Monte Carlo." Thesis, University of Edinburgh, 2016. http://hdl.handle.net/1842/20978.

Full text
Abstract:
Markov chain Monte Carlo (MCMC) is one of the most popular statistical inference methods in machine learning. Recent work shows that a significant improvement of the statistical efficiency of MCMC on complex distributions can be achieved by exploiting geometric properties of the target distribution. This is known as geometric MCMC. However, many such methods, like Riemannian manifold Hamiltonian Monte Carlo (RMHMC), are computationally challenging to scale up to high dimensional distributions. The primary goal of this thesis is to develop novel geometric MCMC methods applicable to large-scale problems. To overcome the computational bottleneck of computing second order derivatives in geometric MCMC, I propose an adaptive MCMC algorithm using an efficient approximation based on Limited memory BFGS. I also propose a simplified variant of RMHMC that is able to work effectively on larger scale than the previous methods. Finally, I address an important limitation of geometric MCMC, namely that is only available for continuous distributions. I investigate a relaxation of discrete variables to continuous variables that allows us to apply the geometric methods. This is a new direction of MCMC research which is of potential interest to many applications. The effectiveness of the proposed methods is demonstrated on a wide range of popular models, including generalised linear models, conditional random fields (CRFs), hierarchical models and Boltzmann machines.
APA, Harvard, Vancouver, ISO, and other styles
48

Desplat, Jean-Christophe. "Monte Carlo simulations of amphiphilic systems." Thesis, Sheffield Hallam University, 1996. http://shura.shu.ac.uk/19557/.

Full text
Abstract:
Results are presented from NVT Monte Carlo simulations of a three-dimensional lattice model of a binary mixture of solvent and surfactant chains in which free self assembly is allowed. It is demonstrated that the model exhibits a critical micelle concentration together with cluster size distributions consistent with experiment and theory (minimum and maximum in the distribution within the micellar region). The weight average aggregation number, N[w], increases linearly with the square root of the concentration of micellised surfactant as predicted theoretically. The dilute solution excess chemical potential (beta[0n] --- beta[01]) is determined from the cluster size distribution. It is found to be a monotonically decreasing function of n with different functional forms for small and large clusters. A single analytical expression is found to describe the cluster size distribution and the X[1] versus X[a] curve on the concentration range from 0 to 5 vol. % . It is necessary to introduce an activity coefficient to accurately describe the behaviour of the model for amphiphile concentrations greater than 5 vol. % . The dependence of this expression on temperature and molecular interaction parameters is determined. Results are also presented for the simulation of longer chains. Following investigation of three of the models free parameters, regions of phase space in which 'spongy' structures and vesicles --- either spherical or tubular --- are successfully identified. A preliminary phase diagram is established by considering the variation in the cavity size distribution function. These results are discussed in relation with experimental data and existing phenomenological studies. An extension of the Configurational-bias Monte Carlo (CBMC) based on a self-avoiding walk using sites selected from subsets of sites known a priori available for the regrowth is also established. Its theoretical fondation is laid out together with a partial assessment of its efficiency relative to both the classic reptation and CBMC for the simulation of chains lying on a lattice of high coordination number. A methodology for the simulation of polyoxyethylene oxide (POE) surfactants using a cubic lattice of coordination number c = 26 is briefly discussed.
APA, Harvard, Vancouver, ISO, and other styles
49

Fang, Youhan. "Efficient Markov Chain Monte Carlo Methods." Thesis, Purdue University, 2018. http://pqdtopen.proquest.com/#viewpdf?dispub=10809188.

Full text
Abstract:

Generating random samples from a prescribed distribution is one of the most important and challenging problems in machine learning, Bayesian statistics, and the simulation of materials. Markov Chain Monte Carlo (MCMC) methods are usually the required tool for this task, if the desired distribution is known only up to a multiplicative constant. Samples produced by an MCMC method are real values in N-dimensional space, called the configuration space. The distribution of such samples converges to the target distribution in the limit. However, existing MCMC methods still face many challenges that are not well resolved. Difficulties for sampling by using MCMC methods include, but not exclusively, dealing with high dimensional and multimodal problems, high computation cost due to extremely large datasets in Bayesian machine learning models, and lack of reliable indicators for detecting convergence and measuring the accuracy of sampling. This dissertation focuses on new theory and methodology for efficient MCMC methods that aim to overcome the aforementioned difficulties.

One contribution of this dissertation is generalizations of hybrid Monte Carlo (HMC). An HMC method combines a discretized dynamical system in an extended space, called the state space, and an acceptance test based on the Metropolis criterion. The discretized dynamical system used in HMC is volume preserving—meaning that in the state space, the absolute Jacobian of a map from one point on the trajectory to another is 1. Volume preservation is, however, not necessary for the general purpose of sampling. A general theory allowing the use of non-volume preserving dynamics for proposing MCMC moves is proposed. Examples including isokinetic dynamics and variable mass Hamiltonian dynamics with an explicit integrator, are all designed with fewer restrictions based on the general theory. Experiments show improvement in efficiency for sampling high dimensional multimodal problems. A second contribution is stochastic gradient samplers with reduced bias. An in-depth analysis of the noise introduced by the stochastic gradient is provided. Two methods to reduce the bias in the distribution of samples are proposed. One is to correct the dynamics by using an estimated noise based on subsampled data, and the other is to introduce additional variables and corresponding dynamics to adaptively reduce the bias. Extensive experiments show that both methods outperform existing methods. A third contribution is quasi-reliable estimates of effective sample size. Proposed is a more reliable indicator—the longest integrated autocorrelation time over all functions in the state space—for detecting the convergence and measuring the accuracy of MCMC methods. The superiority of the new indicator is supported by experiments on both synthetic and real problems.

Minor contributions include a general framework of changing variables, and a numerical integrator for the Hamiltonian dynamics with fourth order accuracy. The idea of changing variables is to transform the potential energy function as a function of the original variable to a function of the new variable, such that undesired properties can be removed. Two examples are provided and preliminary experimental results are obtained for supporting this idea. The fourth order integrator is constructed by combining the idea of the simplified Takahashi-Imada method and a two-stage Hessian-based integrator. The proposed method, called two-stage simplified Takahashi-Imada method, shows outstanding performance over existing methods in high-dimensional sampling problems.

APA, Harvard, Vancouver, ISO, and other styles
50

Jaeckel, Alain. "Simulations Monte Carlo de chaînes confinées." Montpellier 2, 1997. http://www.theses.fr/1997MON20206.

Full text
Abstract:
Par simulation monte carlo (smc), nous generons a l'ordinateur des chemins statistiques (rfws) ou auto-evitants (saws) a l'interieur de pores spheriques de rayons variables. Ces chemins modelisent respectivement des chaines polymere confinees en solvant theta et en bon solvant. A partir des chaines ainsi construites, on estime les dimensions moyennes usuelles (distance moyenne bout a bout et rayon de giration moyen), les distributions des milieux et des extremites ou tous maillons confondus dans la sphere de confinement, la variation d'entropie en fonction du confinement impose et enfin la pression exercee par la chaine sur la surface de confinement. Nous donnons egalement une relation universelle entre le nombre de conformations d'une chaine de n pas, quel que soit son type, et un parametre de compacite determine par smc. Nous proposons aussi une extension de la theorie des blobs de de gennes. Nous discutons nos resultats au vu de resultats theoriques ou de publications anterieures. Nous etablissons l'existence de lois d'echelle, moyennant l'utilisation de parametres de reduction specifiques a chaque type de chaines (rfws ou saws), et montrons que rfws et saws presentent des comportements comparables pour des valeurs egales du rayon reduit de la sphere de confinement. Ainsi, certaines proprietes des saws confines dans des spheres peuvent etre deduits des resultats theoriques plus accessibles des rfws confines en tenant compte d'une simple renormalisation des dimensions, et ce avec un degre d'approximation satisfaisant, voire bon. Nous etendons nos smc au cas des parcours hamiltoniens dont le nombre peut etre estime, pour un carre de cote donne, via l'utilisation d'une loi d'echelle empirique que nous avons etablie. Enfin, nous avons cherche a elucider un vieux probleme de la litterature qui concerne l'exposant d'echelle et la dimension critique des chaines auto-evitantes generees par la procedure reflechissante non ponderee de rosenbluth et rosenbluth.
APA, Harvard, Vancouver, ISO, and other styles
You might also be interested in the bibliographies on the topic 'La Monte' for other source types:
Journal articles Books
We offer discounts on all premium plans for authors whose works are included in thematic literature selections. Contact us to get a unique promo code!

To the bibliography