Добірка наукової літератури з теми "Minimax rate"

Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями

Оберіть тип джерела:

Ознайомтеся зі списками актуальних статей, книг, дисертацій, тез та інших наукових джерел на тему "Minimax rate".

Біля кожної праці в переліку літератури доступна кнопка «Додати до бібліографії». Скористайтеся нею – і ми автоматично оформимо бібліографічне посилання на обрану працю в потрібному вам стилі цитування: APA, MLA, «Гарвард», «Чикаго», «Ванкувер» тощо.

Також ви можете завантажити повний текст наукової публікації у форматі «.pdf» та прочитати онлайн анотацію до роботи, якщо відповідні параметри наявні в метаданих.

Статті в журналах з теми "Minimax rate"

1

Bose, N. K., and C. Charoenlarpnopparut. "Minimax controller design using rate feedback." Circuits, Systems, and Signal Processing 18, no. 1 (January 1999): 17–25. http://dx.doi.org/10.1007/bf01206542.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
2

Bu, Yuheng, Shaofeng Zou, Yingbin Liang, and Venugopal V. Veeravalli. "Estimation of KL Divergence: Optimal Minimax Rate." IEEE Transactions on Information Theory 64, no. 4 (April 2018): 2648–74. http://dx.doi.org/10.1109/tit.2018.2805844.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
3

Bose, N. K., and C. Charoenlarpnopparut. "Minimax controller using rate feedback: Latest results." IFAC Proceedings Volumes 32, no. 2 (July 1999): 3714–19. http://dx.doi.org/10.1016/s1474-6670(17)56635-5.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
4

Gao, Wei. "Minimax Learning Rate for Multi-dividing Ontology Algorithm." Journal of Information and Computational Science 11, no. 6 (April 10, 2014): 1853–60. http://dx.doi.org/10.12733/jics20103216.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
5

Yuhong Yang. "Minimax rate adaptive estimation over continuous hyper-parameters." IEEE Transactions on Information Theory 47, no. 5 (July 2001): 2081–85. http://dx.doi.org/10.1109/18.930947.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
6

Carpentier, A., O. Collier, L. Comminges, A. B. Tsybakov, and Yu Wang. "Minimax Rate of Testing in Sparse Linear Regression." Automation and Remote Control 80, no. 10 (October 2019): 1817–34. http://dx.doi.org/10.1134/s0005117919100047.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
7

Zhao, Puning, and Lifeng Lai. "Minimax Rate Optimal Adaptive Nearest Neighbor Classification and Regression." IEEE Transactions on Information Theory 67, no. 5 (May 2021): 3155–82. http://dx.doi.org/10.1109/tit.2021.3062078.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
8

Wang, Jane-Ling. "Asymptotically Minimax Estimators for Distributions with Increasing Failure Rate." Annals of Statistics 14, no. 3 (September 1986): 1113–31. http://dx.doi.org/10.1214/aos/1176350053.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
9

Wiest, E. J., and E. Polak. "On the rate of convergence of two minimax algorithms." Journal of Optimization Theory and Applications 71, no. 1 (October 1991): 1–30. http://dx.doi.org/10.1007/bf00940037.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
10

Geraniotis, E., and H. Poor. "Minimax discrimination for observed Poisson processes with uncertain rate functions." IEEE Transactions on Information Theory 31, no. 5 (September 1985): 660–69. http://dx.doi.org/10.1109/tit.1985.1057091.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.

Дисертації з теми "Minimax rate"

1

Benhaddou, Rida. "Nonparametric and Empirical Bayes Estimation Methods." Doctoral diss., University of Central Florida, 2013. http://digital.library.ucf.edu/cdm/ref/collection/ETD/id/5765.

Повний текст джерела
Анотація:
In the present dissertation, we investigate two different nonparametric models; empirical Bayes model and functional deconvolution model. In the case of the nonparametric empirical Bayes estimation, we carried out a complete minimax study. In particular, we derive minimax lower bounds for the risk of the nonparametric empirical Bayes estimator for a general conditional distribution. This result has never been obtained previously. In order to attain optimal convergence rates, we use a wavelet series based empirical Bayes estimator constructed in Pensky and Alotaibi (2005). We propose an adaptive version of this estimator using Lepski's method and show that the estimator attains optimal convergence rates. The theory is supplemented by numerous examples. Our study of the functional deconvolution model expands results of Pensky and Sapatinas (2009, 2010, 2011) to the case of estimating an (r+1)-dimensional function or dependent errors. In both cases, we derive minimax lower bounds for the integrated square risk over a wide set of Besov balls and construct adaptive wavelet estimators that attain those optimal convergence rates. In particular, in the case of estimating a periodic (r+1)-dimensional function, we show that by choosing Besov balls of mixed smoothness, we can avoid the ''curse of dimensionality'' and, hence, obtain higher than usual convergence rates when r is large. The study of deconvolution of a multivariate function is motivated by seismic inversion which can be reduced to solution of noisy two-dimensional convolution equations that allow to draw inference on underground layer structures along the chosen profiles. The common practice in seismology is to recover layer structures separately for each profile and then to combine the derived estimates into a two-dimensional function. By studying the two-dimensional version of the model, we demonstrate that this strategy usually leads to estimators which are less accurate than the ones obtained as two-dimensional functional deconvolutions. Finally, we consider a multichannel deconvolution model with long-range dependent Gaussian errors. We do not limit our consideration to a specific type of long-range dependence, rather we assume that the eigenvalues of the covariance matrix of the errors are bounded above and below. We show that convergence rates of the estimators depend on a balance between the smoothness parameters of the response function, the smoothness of the blurring function, the long memory parameters of the errors, and how the total number of observations is distributed among the channels.
Ph.D.
Doctorate
Mathematics
Sciences
Mathematics
Стилі APA, Harvard, Vancouver, ISO та ін.
2

Fermanian, Jean-Baptiste. "High dimensional multiple means estimation and testing with applications to machine learning." Electronic Thesis or Diss., université Paris-Saclay, 2024. http://www.theses.fr/2024UPASM035.

Повний текст джерела
Анотація:
Nous étudions dans cette thèse l'influence de la grande dimension dans des problèmes de test et d'estimation. Notre analyse porte sur la dépendance en la dimension de la vitesse de séparation d'un test de proximité et du risque quadratique de l'estimation multiples de vecteurs. Nous complétons les résultats existants en étudiant ces dépendances dans le cas de distributions non isotropes. Pour de telles distributions, le rôle de la dimension est alors joué par des notions de dimension effective définies à partir de la covariance des distributions. Ce cadre permet d'englober des données de dimension infinie comme le kernel mean embedding, outil de machine learning que nous chercherons à estimer. A l'aide de cette analyse, nous construisons des méthodes d'estimation simultanée de vecteurs moyennes de différentes distributions à partir d'échantillons indépendants de chacune. Ces estimateurs ont de meilleures performances théorique et pratique relativement aux moyennes empiriques, en particulier dans des situations défavorables où la dimension (effective) est grande. Ces méthodes utilisent explicitement ou implicitement la relative facilité du test par rapport à l'estimation. Elles reposent sur la construction d'estimateurs de distances et de moments de la covariance pour lesquels nous fournissons des bornes de concentration non asymptotiques. Un intérêt particulier est porté à l'étude de données bornées pour lesquels une analyse spécifique est nécessaire. Nos méthodes sont accompagnées d'une analyse minimax justifiant leur optimalité. Dans une dernière partie, nous proposons une interprétation du mécanisme d'attention utilisé dans les réseaux de neurones Transformers comme un problème d'estimation multiple de vecteurs. Dans un cadre simplifié, ce mécanisme partage des idées similaires avec nos approches et nous mettons en évidence son effet de débruitage en grande dimension
In this thesis, we study the influence of high dimension in testing and estimation problems. We analyze the dimension dependence of the separation rate of a closeness test and of the quadratic risk of multiple vector estimation. We complement existing results by studying these dependencies in the case of non-isotropic distributions. For such distributions, the role of dimension is played by notions of effective dimension defined from the covariance of the distributions. This framework covers infinite-dimensional data such as kernel mean embedding, a machine learning tool we will be seeking to estimate. Using this analysis, we construct methods for simultaneously estimating mean vectors of different distributions from independent samples of each. These estimators perform better theoretically and practically than the empirical mean in unfavorable situations where the (effective) dimension is large. These methods make explicit or implicit use of the relative ease of testing compared with estimation. They are based on the construction of estimators of distances and moments of covariance, for which we provide non-asymptotic concentration bounds. Particular interest is given to the study of bounded data, for which a specific analysis is required. Our methods are accompanied by a minimax analysis justifying their optimality. In a final section, we propose an interpretation of the attention mechanism used in Transformer neural networks as a multiple vector estimation problem. In a simplified framework, this mechanism shares similar ideas with our approaches, and we highlight its denoising effect in high dimension
Стилі APA, Harvard, Vancouver, ISO та ін.
3

Tan, Shuang. "Minimum error rate beamforming transceivers." Thesis, University of Southampton, 2008. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.446595.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
4

Huang, Chiao Ching Baskiyar Sanjeev. "Minimum power consumption for rate monotonic tasks." Auburn, Ala, 2008. http://repo.lib.auburn.edu/EtdRoot/2008/FALL/Computer_Science_and_Software_Engineering/Thesis/Huang_Chiao_10.pdf.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
5

Bage, Jayaraj Nagendra. "Minimum Symbol Error Rate Timing Recovery System." DigitalCommons@USU, 2010. https://digitalcommons.usu.edu/etd/684.

Повний текст джерела
Анотація:
This thesis presents a timing error detector (TED) used in the symbol timing synchronization subsystem for digital communications. The new timing error detector is designed to minimize the probability of symbol decision error, and it is called minimum symbol error rate TED (MSERTED). The new TED resembles the TED derived using the maximum likelihood (ML) criterion but gives rise to faster convergence relative to MLTED. The new TED requires shorter training sequences for symbol timing recovery. The TED operates on the outputs of the matched filter and estimates the timing offset. The S-curve is used as a tool for analyzing the behavior of the TEDs. The faster convergence of the new TED is shown in simulation results as compared to MLTED. The new TED works well for any two-dimensional constellation with arbitrarily shaped decision regions.
Стилі APA, Harvard, Vancouver, ISO та ін.
6

Jeunesse, Paulien. "Estimation non paramétrique du taux de mort dans un modèle de population générale : Théorie et applications. A new inference strategy for general population mortality tables Nonparametric adaptive inference of birth and death models in a large population limit Nonparametric inference of age-structured models in a large population limit with interactions, immigration and characteristics Nonparametric test of time dependance of age-structured models in a large population limit." Thesis, Paris Sciences et Lettres (ComUE), 2019. http://www.theses.fr/2019PSLED013.

Повний текст джерела
Анотація:
L’étude du taux de mortalité dans des modèles de population humaine ou en biologie est le cœur de ce travail. Cette thèse se situe à la frontière de la statistique des processus, de la statistique non-paramétrique et de l’analyse.Dans une première partie, centrée sur une problématique actuarielle, un algorithme est proposé pour estimer les tables de mortalité, utiles en assurance. Cet algorithme se base sur un modèle déterministe de population. Ces nouvelles estimations améliorent les résultats actuels en prenant en compte la dynamique globale de la population. Ainsi les naissances sont incorporées dans le modèle pour calculer le taux de mort. De plus, ces estimations sont mises en lien avec les travaux précédents, assurant ainsi la continuité théorique de notre travail.Dans une deuxième partie, nous nous intéressons à l’estimation du taux de mortalité dans un modèle stochastique de population. Cela nous pousse à utiliser des arguments propres à la statistique des processus et à la statistique non-paramétrique. On trouve alors des estimateurs non-paramétriques adaptatifs dans un cadre anisotrope pour la mortalité et la densité de population, ainsi que des inégalités de concentration non asymptotiques quantifiant la distance entre le modèle stochastique et le modèle déterministe limite utilisé dans la première partie. On montre que ces estimateurs restent optimaux dans un modèle où le taux de mort dépend d’interactions, comme dans le cas de la population logistique.Dans une troisième partie, on considère la réalisation d’un test pour détecter la présence d’interactions dans le taux de mortalité. Ce test permet en réalité de juger de la dépendance temporelle de ce taux. Sous une hypothèse, on montre alors qu’il est possible de détecter la présence d’interactions. Un algorithme pratique est proposé pour réaliser ce test
In this thesis, we study the mortality rate in different population models to apply our results to demography or biology. The mathematical framework includes statistics of process, nonparametric estimations and analysis.In a first part, an algorithm is proposed to estimate the mortality tables. This problematic comes from actuarial science and the aim is to apply our results in the insurance field. This algorithm is founded on a deterministic population model. The new estimates we gets improve the actual results. Its advantage is to take into account the global population dynamics. Thanks to that, births are used in our model to compute the mortality rate. Finally these estimations are linked with the precedent works. This is a point of great importance in the field of actuarial science.In a second part, we are interested in the estimation of the mortality rate in a stochastic population model. We need to use the tools coming from nonparametric estimations and statistics of process to do so. Indeed, the mortality rate is a function of two parameters, the time and the age. We propose minimax optimal and adaptive estimators for the mortality and the population density. We also demonstrate some non asymptotics concentration inequalities. These inequalities quantifiy the deviation between the stochastic process and its deterministic limit we used in the first part. We prove that our estimators are still optimal in a model where the mortality is influenced by interactions. This is for example the case for the logistic population.In a third part, we consider the testing problem to detect the existence of interactions. This test is in fact designed to detect the time dependance of the mortality rate. Under the assumption the time dependance in the mortality rate comes only from the interactions, we can detect the presence of interactions. Finally we propose an algorithm to do this test
Стилі APA, Harvard, Vancouver, ISO та ін.
7

Veneri, Matteo. "Minimum-lap-time of race vehicles." Doctoral thesis, Università degli studi di Padova, 2019. http://hdl.handle.net/11577/3425794.

Повний текст джерела
Анотація:
This work deals with the numerical-optimisation methods employed for assessing the minimum-lap-time of race vehicles. A particular emphasis is given to the simulations based on the solution of an optimal-control problem. First, a detailed review is devoted to the optimal-control theory, including direct and indirect methods, together with explicit and implicit formulations. Three vehicle models are proposed for the implementation in steady-state and dynamic simulations. A steady-state double-track race-car model is presented first, implementing aerodynamic forces, Pacejka-based tyre model, fixed brake-ratio and steady-state lateral-load transfer. This model is then extended including the transient effects for the implementation in a dynamic minimum-time simulation. An essential but comprehensive steady-state motorcycle model is also presented, retaining the peculiar aspects of the motorcycle dynamics, such as the wheelie and stoppie conditions, while assuming the optimal braking-bias. Then, an optimisation program is developed for computing the race car g-g envelope. A different approach is shown for the steady-state motorcycle model, which is employed for computing the g-g diagrams analytically. Finally, the most widespread minimum-lap-time simulations are discussed and developed for the presented models, including a quasi-steady-state fixed-trajectory apex-finding approach and a quasi-steady-state fixed-trajectory optimal-control simulation. In addition, a novel approach that combines a steady-state vehicle model with the trajectory optimisation is presented and compared to the discussed simulations. This approach builds upon the formulation of an optimal-control problem and employs the g-g diagrams for limiting the vehicle performance. The results are employed for a sensitivity analysis, that underlines the effect of different parameters on the resulting race line. A dynamic race car model is also implemented in a free-trajectory optimal-control simulation. This program is employed for analysing the effect of different steering geometries on the vehicle performance in different test manoeuvres and during a track lap.
Стилі APA, Harvard, Vancouver, ISO та ін.
8

Samingan, Ahmad Kamsani. "Minimum bit error rate multiuser detection techniques for DS-CDMA." Thesis, University of Southampton, 2003. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.398594.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
9

Prescott, Lisa. "The minimum acceptable rate of return, engineering economic theory and practice." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 1999. http://www.collectionscanada.ca/obj/s4/f2/dsk1/tape7/PQDD_0020/MQ47082.pdf.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
10

Alias, Mohamad Yusoff. "Minimum bit error rate multiuser detection for multiple antenna aided uplink OFDM." Thesis, University of Southampton, 2004. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.432466.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.

Книги з теми "Minimax rate"

1

Library of Congress. Congressional Research Service, ed. Indexing the federal minimum wage rate: Methodologies and calculated results. [Washington, D.C.]: Congressional Research Service, Library of Congress, 1992.

Знайти повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
2

Congress, Trades Union. National minimum wage development rate: Young people : what do they know?. London: Trades Union Congress, 2002.

Знайти повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
3

A, Subrahmanya R. K., Parduman Singh, Social Security Association of India., and Friedrich-Ebert-Stiftung (India), eds. Minimum wages in India: Scheduled employments and rates of minimum wages. New Delhi: Social Security Association of India, 1995.

Знайти повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
4

Bradley, Cheryl E. Status of the Tiny Cryptanthe (Cryptantha minima) in Alberta. [Edmonton]: Alberta Sustainable Resource Development, 2004.

Знайти повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
5

Congress, Trades Union. Wage rage: A report on what is making Britain's low paid angry. [London]: TUC, 1997.

Знайти повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
6

Cox, Gabrielle. After the safety net: A study of pay rates in wages council sectors post abolition. Manchester: Low Pay Network, 1994.

Знайти повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
7

Lim, Chee Peng. Minimal error rate classification in a non-stationary environment via a modified fuzzy ARTMAP network. Sheffield: University of Sheffield, Dept. of Automatic Control & Systems Engineering, 1995.

Знайти повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
8

Feenberg, Daniel. The alternative minimum tax and effective marginal tax rates. Cambridge, Mass: National Bureau of Economic Research, 2003.

Знайти повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
9

Feenberg, Daniel. The alternative minimum tax and effective marginal tax rates. Cambridge, MA: Massachusetts Institute of Technology, Dept. of Economics, 2003.

Знайти повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
10

Congress, Trades Union. Wage rage: A report on what is making Britain's low paid angry in the South East. [London]: TUC, 1997.

Знайти повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.

Частини книг з теми "Minimax rate"

1

Yang, Liu, Steve Hanneke, and Jaime Carbonell. "Bounds on the Minimax Rate for Estimating a Prior over a VC Class from Independent Learning Tasks." In Lecture Notes in Computer Science, 270–84. Cham: Springer International Publishing, 2015. http://dx.doi.org/10.1007/978-3-319-24486-0_18.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
2

Margaritescu, Irina, and A. Doru Chirita. "Minimal Deviation Melanoma/Nevoid Melanoma." In Rare Malignant Skin Tumors, 227–29. New York, NY: Springer New York, 2014. http://dx.doi.org/10.1007/978-1-4939-2023-5_51.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
3

Szathmary, Laszlo, Petko Valtchev, and Amedeo Napoli. "Finding Minimal Rare Itemsets and Rare Association Rules." In Knowledge Science, Engineering and Management, 16–27. Berlin, Heidelberg: Springer Berlin Heidelberg, 2010. http://dx.doi.org/10.1007/978-3-642-15280-1_5.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
4

von Wolff, Michael, and Isotta Magaton. "Success Rates of Natural Cycle and Minimal Stimulation IVF." In Natural Cycle and Minimal Stimulation IVF, 185–96. Cham: Springer International Publishing, 2022. http://dx.doi.org/10.1007/978-3-030-97571-5_19.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
5

Capillar, Elieser, Chowdhury Abdul Mumin Ishmam, Carson K. Leung, Adam G. M. Pazdor, Prabhanshu Shrivastava, and Ngoc Bao Chau Truong. "Bitwise Vertical Mining of Minimal Rare Patterns." In Big Data Analytics and Knowledge Discovery, 135–41. Cham: Springer Nature Switzerland, 2023. http://dx.doi.org/10.1007/978-3-031-39831-5_13.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
6

Wang, Can, Yang Liu, and Maosong Sun. "Minimum Error Rate Training for Bilingual News Alignment." In Lecture Notes in Computer Science, 425–35. Berlin, Heidelberg: Springer Berlin Heidelberg, 2013. http://dx.doi.org/10.1007/978-3-642-45185-0_45.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
7

Wu, Hao, and Zhipei Zhang. "Theory of Minimum Dissipation Rate in Fluid Dynamics." In Proceedings of the 2023 5th International Conference on Civil Engineering, Environment Resources and Energy Materials (CCESEM 2023), 219–35. Dordrecht: Atlantis Press International BV, 2023. http://dx.doi.org/10.2991/978-94-6463-316-0_24.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
8

Cruz-Sampedro, J., and M. Tetlalmatzi-Montiel. "Minimum Resistance in a Rare Medium." In Experimental and Computational Fluid Mechanics, 129–45. Cham: Springer International Publishing, 2013. http://dx.doi.org/10.1007/978-3-319-00116-6_9.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
9

Organ, S. J., A. Keller, and G. Ungar. "Growth, Nucleation and Thickening Rate Minima in Long Linear Alkanes." In Crystallization of Polymers, 81–86. Dordrecht: Springer Netherlands, 1993. http://dx.doi.org/10.1007/978-94-011-1950-4_8.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
10

Gonzalez-Alberquilla, Rodrigo, Karin Strauss, Luis Ceze, and Luis Piñuel. "Accelerating Data Race Detection with Minimal Hardware Support." In Euro-Par 2011 Parallel Processing, 27–38. Berlin, Heidelberg: Springer Berlin Heidelberg, 2011. http://dx.doi.org/10.1007/978-3-642-23400-2_4.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.

Тези доповідей конференцій з теми "Minimax rate"

1

Mahmood, Adeel, and Aaron B. Wagner. "Minimax Rate-Distortion." In 2022 IEEE International Symposium on Information Theory (ISIT). IEEE, 2022. http://dx.doi.org/10.1109/isit50566.2022.9834588.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
2

Rezaei, Farzad, Charalambos D. Charalambous, Photios A. Stavrou, and Christos Kourtellaris. "Minimax rate distortion for a class of sources." In 2010 4th International Symposium on Communications, Control and Signal Processing (ISCCSP). IEEE, 2010. http://dx.doi.org/10.1109/isccsp.2010.5463428.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
3

Tam, W. P., and T. M. Lok. "Rate Allocation for the Multi-Source Downlink Channel with Minimax Optimization." In ICC 2009 - 2009 IEEE International Conference on Communications. IEEE, 2009. http://dx.doi.org/10.1109/icc.2009.5199389.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
4

Yuan, Meng, and Junzo Watada. "A minimax model of portfolio optimization using data mining to predict interval return rate." In 2014 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE). IEEE, 2014. http://dx.doi.org/10.1109/fuzz-ieee.2014.6891693.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
5

Gao, Hongchang, Xiaoqian Wang, Lei Luo, and Xinghua Shi. "On the Convergence of Stochastic Compositional Gradient Descent Ascent Method." In Thirtieth International Joint Conference on Artificial Intelligence {IJCAI-21}. California: International Joint Conferences on Artificial Intelligence Organization, 2021. http://dx.doi.org/10.24963/ijcai.2021/329.

Повний текст джерела
Анотація:
The compositional minimax problem covers plenty of machine learning models such as the distributionally robust compositional optimization problem. However, it is yet another understudied problem to optimize the compositional minimax problem. In this paper, we develop a novel efficient stochastic compositional gradient descent ascent method for optimizing the compositional minimax problem. Moreover, we establish the theoretical convergence rate of our proposed method. To the best of our knowledge, this is the first work achieving such a convergence rate for the compositional minimax problem. Finally, we conduct extensive experiments to demonstrate the effectiveness of our proposed method.
Стилі APA, Harvard, Vancouver, ISO та ін.
6

Zhang, Yihan, Meikang Qiu, and Hongchang Gao. "Communication-Efficient Stochastic Gradient Descent Ascent with Momentum Algorithms." In Thirty-Second International Joint Conference on Artificial Intelligence {IJCAI-23}. California: International Joint Conferences on Artificial Intelligence Organization, 2023. http://dx.doi.org/10.24963/ijcai.2023/512.

Повний текст джерела
Анотація:
Numerous machine learning models can be formulated as a stochastic minimax optimization problem, such as imbalanced data classification with AUC maximization. Developing efficient algorithms to optimize such kinds of problems is of importance and necessity. However, most existing algorithms restrict their focus on the single-machine setting so that they are incapable of dealing with the large communication overhead in a distributed training system. Moreover, most existing communication-efficient optimization algorithms only focus on the traditional minimization problem, failing to handle the minimax optimization problem. To address these challenging issues, in this paper, we develop two novel communication-efficient stochastic gradient descent ascent with momentum algorithms for the distributed minimax optimization problem, which can significantly reduce the communication cost via the two-way compression scheme. However, the compressed momentum makes it considerably challenging to investigate the convergence rate of our algorithms, especially in the presence of the interaction between the minimization and maximization subproblems. In this paper, we successfully addressed these challenges and established the convergence rate of our algorithms for nonconvex-strongly-concave problems. To the best of our knowledge, our algorithms are the first communication-efficient algorithm with theoretical guarantees for the minimax optimization problem. Finally, we apply our algorithm to the distributed AUC maximization problem for the imbalanced data classification task. Extensive experimental results confirm the efficacy of our algorithm in saving communication costs.
Стилі APA, Harvard, Vancouver, ISO та ін.
7

Wang, Di, and Jinhui Xu. "Principal Component Analysis in the Local Differential Privacy Model." In Twenty-Eighth International Joint Conference on Artificial Intelligence {IJCAI-19}. California: International Joint Conferences on Artificial Intelligence Organization, 2019. http://dx.doi.org/10.24963/ijcai.2019/666.

Повний текст джерела
Анотація:
In this paper, we study the Principal Component Analysis (PCA) problem under the (distributed) non-interactive local differential privacy model. For the low dimensional case, we show the optimal rate for the private minimax risk of the k-dimensional PCA using the squared subspace distance as the measurement. For the high dimensional row sparse case, we first give a lower bound on the private minimax risk, . Then we provide an efficient algorithm to achieve a near optimal upper bound. Experiments on both synthetic and real world datasets confirm the theoretical guarantees of our algorithms.
Стилі APA, Harvard, Vancouver, ISO та ін.
8

Wang, Shaowei, Jin Li, Yuqiu Qian, Jiachun Du, Wenqing Lin, and Wei Yang. "Hiding Numerical Vectors in Local Private and Shuffled Messages." In Thirtieth International Joint Conference on Artificial Intelligence {IJCAI-21}. California: International Joint Conferences on Artificial Intelligence Organization, 2021. http://dx.doi.org/10.24963/ijcai.2021/510.

Повний текст джерела
Анотація:
Numerical vector aggregation has numerous applications in privacy-sensitive scenarios, such as distributed gradient estimation in federated learning, and statistical analysis on key-value data. Within the framework of local differential privacy, this work gives tight minimax error bounds of O(d s/(n epsilon^2)), where d is the dimension of the numerical vector and s is the number of non-zero entries. An attainable mechanism is then designed to improve from existing approaches suffering error rate of O(d^2/(n epsilon^2)) or O(d s^2/(n epsilon^2)). To break the error barrier in the local privacy, this work further consider privacy amplification in the shuffle model with anonymous channels, and shows the mechanism satisfies centralized (14 ln(2/delta) (s e^epsilon+2s-1)/(n-1))^0.5, delta)-differential privacy, which is domain independent and thus scales to federated learning of large models. We experimentally validate and compare it with existing approaches, and demonstrate its significant error reduction.
Стилі APA, Harvard, Vancouver, ISO та ін.
9

Duchi, John C., Michael I. Jordan, and Martin J. Wainwright. "Local privacy and statistical minimax rates." In 2013 51st Annual Allerton Conference on Communication, Control, and Computing (Allerton). IEEE, 2013. http://dx.doi.org/10.1109/allerton.2013.6736718.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
10

Duchi, John C., Michael I. Jordan, and Martin J. Wainwright. "Local Privacy and Statistical Minimax Rates." In 2013 IEEE 54th Annual Symposium on Foundations of Computer Science (FOCS). IEEE, 2013. http://dx.doi.org/10.1109/focs.2013.53.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.

Звіти організацій з теми "Minimax rate"

1

Royset, J. O., and E. Y. Pee. Rate of Convergence Analysis of Discretization and Smoothing Algorithms for Semi-Infinite Minimax Problems. Fort Belvoir, VA: Defense Technical Information Center, June 2011. http://dx.doi.org/10.21236/ada551990.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
2

Sinn, Hans-Werner, and Michael Reutter. The Minimum Inflation Rate for Euroland. Cambridge, MA: National Bureau of Economic Research, January 2001. http://dx.doi.org/10.3386/w8085.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
3

Graham, Bryan, Fengshi Niu, and James Powell. Minimax Risk and Uniform Convergence Rates for Nonparametric Dyadic Regression. Cambridge, MA: National Bureau of Economic Research, March 2021. http://dx.doi.org/10.3386/w28548.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
4

Bird, Lori, Carolyn Davidson, Joyce McLaren, and John Miller. Impact of Rate Design Alternatives on Residential Solar Customer Bills. Increased Fixed Charges, Minimum Bills and Demand-based Rates. Office of Scientific and Technical Information (OSTI), September 2015. http://dx.doi.org/10.2172/1225307.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
5

Ávila-Montealegre, Oscar Iván, Anderson Grajales-Olarte, Juan J. Ospina-Tejeiro, and Mario A. Ramos-Veloza. Minimum Wage and Macroeconomic Adjustment: Insights from a Small Open, Emerging, Economy with Formal and Informal Labor. Banco de la República, December 2023. http://dx.doi.org/10.32468/be.1264.

Повний текст джерела
Анотація:
We examine the adjustment of a small, open, emerging market economy (SOEME) to an unexpected increase in the minimum wage using an extended New-Keynesian SOE model that incorporates heterogeneous households, a flexible production structure, and a minimum wage rule. We calibrate the model for Colombia and find that an unexpected increase in the minimum wage has significant effects on the low-skilled labor market, and weaker impacts on inflation and the policy interest rate. The rise in the minimum wage increases production costs and prompts the substitution of formal low-skilled labor with informal workers and machinery, resulting in reduced output, increased inflation, and higher policy interest rates. We also observe that the minimum wage influences the transmission of productivity, demand, and monetary shocks, leading to a more persistent impact on macroeconomic variables, and a less efficient monetary policy to control inflation. Our findings suggest that the minimum wage has important macroeconomic implications, and affects emerging market economies through different channels than in developed economies.
Стилі APA, Harvard, Vancouver, ISO та ін.
6

Poirier, M. R. Minimum Sparge Rate to Suspend Solid Particles in the 2H-Evaporator. Office of Scientific and Technical Information (OSTI), September 2000. http://dx.doi.org/10.2172/763272.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
7

Edeh, Henry, C. Assessing the Equity and Redistributive Effects of Taxation Reforms in Nigeria. Institute of Development Studies, April 2023. http://dx.doi.org/10.19088/ictd.2023.016.

Повний текст джерела
Анотація:
Nigeria’s annual economic growth averaged 7.1 per cent in the 2000s, but the 2014–15 oil shock and Covid-19 reversed this, with growth now averaging only 0.7 per cent. Living standards have fallen as population growth has outpaced economic growth. The poverty rate has risen from 35 per cent in 2010 to 41 per cent in 2019, and inequality has only declined slightly. Changing the structure of fiscal taxation instruments could significantly impact growth, income distribution and poverty levels. The government has made some tax reforms, amending the Personal Income Tax (PIT) Act 1993 with acts in 2004 and 2011. The 2011 Act made changes in tax rates, tax bands, minimum rate and relief allowance: the tax rate for the lowest income earners was reduced from 7 to 5 per cent in the post-2011 scheme. Summary of ICTD Working Paper 130 by Henry C. Edeh.
Стилі APA, Harvard, Vancouver, ISO та ін.
8

Feenberg, Daniel, and James Poterba. The Alternative Minimum Tax and Effective Marginal Tax Rates. Cambridge, MA: National Bureau of Economic Research, November 2003. http://dx.doi.org/10.3386/w10072.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
9

Vogel, Jonathan. The Race Between Education, Technology, and the Minimum Wage. Cambridge, MA: National Bureau of Economic Research, March 2023. http://dx.doi.org/10.3386/w31028.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
10

Boning, William, Drahomir Klimsa, Joel Slemrod, and Robert Ullmann. Norderfriedrichskoog! Tax Havens, Tax Competition and the Introduction of a Minimum Tax Rate. Cambridge, MA: National Bureau of Economic Research, May 2023. http://dx.doi.org/10.3386/w31225.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
Ми пропонуємо знижки на всі преміум-плани для авторів, чиї праці увійшли до тематичних добірок літератури. Зв'яжіться з нами, щоб отримати унікальний промокод!

До бібліографії