[Représentation duale des φ-divergences et applications]
Dans cette Note, nous donnons une représentation « duale » des divergences. Nous utilisons cette représentation pour définir et étudier de nouveaux estimateurs de la loi et des divergences pour des modèles paramétriques discrets et continus.
In this Note, we give a “dual” representation of divergences. We make use of this representation to define and study some new estimates of the law and of the divergences for discrete and continuous parametric models.
Accepté le :
Publié le :
Amor Keziou 1
@article{CRMATH_2003__336_10_857_0, author = {Amor Keziou}, title = {Dual representation of \protect\emph{\ensuremath{\varphi}}-divergences and applications}, journal = {Comptes Rendus. Math\'ematique}, pages = {857--862}, publisher = {Elsevier}, volume = {336}, number = {10}, year = {2003}, doi = {10.1016/S1631-073X(03)00215-2}, language = {en}, }
Amor Keziou. Dual representation of φ-divergences and applications. Comptes Rendus. Mathématique, Volume 336 (2003) no. 10, pp. 857-862. doi : 10.1016/S1631-073X(03)00215-2. https://comptes-rendus.academie-sciences.fr/mathematique/articles/10.1016/S1631-073X(03)00215-2/
[1] M. Broniatowski, Estimation through Kullback–Leibler divergence, Math. Methods Statist. (2003) (submitted)
[2] Multinomial goodness-of-fit tests, J. Roy. Statist. Soc. Ser. B, Volume 46 (1984) no. 3, pp. 440-464
[3] On topological properties of f-divergences, Studia Sci. Math. Hungar., Volume 2 (1967), pp. 329-339
[4] Large Deviations Techniques and Applications, Jones & Bartlett, 1998
[5] Convex Statistical Distances, Teubner, Leipzig, 1987
[6] Efficiency versus robustness: the case for minimum Hellinger distance and related methods, Ann. Statist., Volume 22 (1994), pp. 1081-1114
[7] Asymptotic divergence of estimates of discrete distributions, J. Statist. Plann. Inference, Volume 48 (1995) no. 3, pp. 347-369
[8] On the minimum discrimination information theorem, Statist. Decisions, Suppl., Volume 1 (1984), pp. 263-283
[9] Asymptotic Statistics, Cambridge Series in Statistical and Probabilitic Mathematics, 1998
- Deep Dimension Reduction for Supervised Representation Learning, IEEE Transactions on Information Theory, Volume 70 (2024) no. 5, p. 3583 | DOI:10.1109/tit.2023.3340658
- Empirical Likelihood with Censored Data, Geometric Science of Information, Volume 14071 (2023), p. 125 | DOI:10.1007/978-3-031-38271-0_13
- Mutual information maximization and feature space separation and bi-bimodal mo-dality fusion for multimodal sentiment analysis, Journal of Intelligent Fuzzy Systems, Volume 45 (2023) no. 4, p. 5783 | DOI:10.3233/jifs-222189
- A Deep Generative Approach to Conditional Sampling, Journal of the American Statistical Association, Volume 118 (2023) no. 543, p. 1837 | DOI:10.1080/01621459.2021.2016424
- Estimating time-dependent entropy production from non-equilibrium trajectories, Communications Physics, Volume 5 (2022) no. 1 | DOI:10.1038/s42005-021-00787-x
- Information-Theoretic Representation Learning for Positive-Unlabeled Classification, Neural Computation, Volume 33 (2021) no. 1, p. 244 | DOI:10.1162/neco_a_01337
- , 2019 Chinese Control And Decision Conference (CCDC) (2019), p. 3016 | DOI:10.1109/ccdc.2019.8832868
- , 2019 International Conference on Image and Vision Computing New Zealand (IVCNZ) (2019), p. 1 | DOI:10.1109/ivcnz48456.2019.8961008
- On Data-Processing and Majorization Inequalities for f-Divergences with Applications, Entropy, Volume 21 (2019) no. 10, p. 1022 | DOI:10.3390/e21101022
- Empirical Estimation of Information Measures: A Literature Guide, Entropy, Volume 21 (2019) no. 8, p. 720 | DOI:10.3390/e21080720
- Large-Margin Label-Calibrated Support Vector Machines for Positive and Unlabeled Learning, IEEE Transactions on Neural Networks and Learning Systems, Volume 30 (2019) no. 11, p. 3471 | DOI:10.1109/tnnls.2019.2892403
- A Weighted Bootstrap Procedure for Divergence Minimization Problems, Analytical Methods in Statistics, Volume 193 (2017), p. 1 | DOI:10.1007/978-3-319-51313-3_1
- Semiparametric Estimation of Mutual Information and Related Criteria: Optimal Test of Independence, IEEE Transactions on Information Theory, Volume 63 (2017) no. 1, p. 57 | DOI:10.1109/tit.2016.2620163
- Class-prior estimation for learning from positive and unlabeled data, Machine Learning, Volume 106 (2017) no. 4, p. 463 | DOI:10.1007/s10994-016-5604-6
- Multivariate Divergences with Application in Multisample Density Ratio Models, Geometric Science of Information, Volume 9389 (2015), p. 444 | DOI:10.1007/978-3-319-25040-3_48
- Generalized Mutual-Information Based Independence Tests, Geometric Science of Information, Volume 9389 (2015), p. 454 | DOI:10.1007/978-3-319-25040-3_49
- Conditional Density Estimation with Dimensionality Reduction via Squared-Loss Conditional Entropy Minimization, Neural Computation, Volume 27 (2015) no. 1, p. 228 | DOI:10.1162/neco_a_00683
- Class Prior Estimation from Positive and Unlabeled Data, IEICE Transactions on Information and Systems, Volume E97.D (2014) no. 5, p. 1358 | DOI:10.1587/transinf.e97.d.1358
- Semi-supervised learning of class balance under class-prior change by distribution matching, Neural Networks, Volume 50 (2014), p. 110 | DOI:10.1016/j.neunet.2013.11.010
- Minimum divergence estimators, maximum likelihood and exponential families, Statistics Probability Letters, Volume 93 (2014), p. 27 | DOI:10.1016/j.spl.2014.06.014
- , 2013 International Winter Workshop on Brain-Computer Interface (BCI) (2013), p. 12 | DOI:10.1109/iww-bci.2013.6506611
- Direct Approximation of Divergences Between Probability Distributions, Empirical Inference (2013), p. 273 | DOI:10.1007/978-3-642-41136-6_23
- Weighted Sampling, Maximum Likelihood and Minimum Divergence Estimators, Geometric Science of Information, Volume 8085 (2013), p. 467 | DOI:10.1007/978-3-642-40020-9_51
- Direct Divergence Approximation between Probability Distributions and Its Applications in Machine Learning, Journal of Computing Science and Engineering, Volume 7 (2013) no. 2, p. 99 | DOI:10.5626/jcse.2013.7.2.99
- Sufficient Dimension Reduction via Squared-Loss Mutual Information Estimation, Neural Computation, Volume 25 (2013) no. 3, p. 725 | DOI:10.1162/neco_a_00407
- Change-point detection in time-series data by relative density-ratio estimation, Neural Networks, Volume 43 (2013), p. 72 | DOI:10.1016/j.neunet.2013.01.012
- A robust algorithm for convolutive blind source separation in presence of noise, Signal Processing, Volume 93 (2013) no. 4, p. 818 | DOI:10.1016/j.sigpro.2012.09.026
- Density-ratio matching under the Bregman divergence: a unified framework of density-ratio estimation, Annals of the Institute of Statistical Mathematics, Volume 64 (2012) no. 5, p. 1009 | DOI:10.1007/s10463-011-0343-8
-
-Divergence Estimation and Two-Sample Homogeneity Test Under Semiparametric Density-Ratio Models, IEEE Transactions on Information Theory, Volume 58 (2012) no. 2, p. 708 | DOI:10.1109/tit.2011.2163380 - Dual Divergence Estimators of the Tail Index, ISRN Probability and Statistics, Volume 2012 (2012), p. 1 | DOI:10.5402/2012/746203
- General Bootstrap for Dual ϕ-Divergence Estimates, Journal of Probability and Statistics, Volume 2012 (2012), p. 1 | DOI:10.1155/2012/834107
- Divergences and duality for estimation and test under moment condition models, Journal of Statistical Planning and Inference, Volume 142 (2012) no. 9, p. 2554 | DOI:10.1016/j.jspi.2012.03.013
- Inference in ϕ-families of distributions, Statistics, Volume 45 (2011) no. 3, p. 223 | DOI:10.1080/02331880903546324
- Estimating Divergence Functionals and the Likelihood Ratio by Convex Risk Minimization, IEEE Transactions on Information Theory, Volume 56 (2010) no. 11, p. 5847 | DOI:10.1109/tit.2010.2068870
- Parametric estimation and tests through divergences and the duality technique, Journal of Multivariate Analysis, Volume 100 (2009) no. 1, p. 16 | DOI:10.1016/j.jmva.2008.03.011
- On empirical likelihood for semiparametric two-sample density ratio models, Journal of Statistical Planning and Inference, Volume 138 (2008) no. 4, p. 915 | DOI:10.1016/j.jspi.2007.02.009
Cité par 36 documents. Sources : Crossref
Commentaires - Politique