Variational Representations and Neural Network Estimation of Rényi Divergences

DOI10.1137/20M1368926zbMath1477.94037arXiv2007.03814OpenAlexW3202864205MaRDI QIDQ5162628

Jeremiah Birrell, Paul Dupuis, Luc Rey-Bellet, Jie Wang, Markos A. Katsoulakis

Publication date: 3 November 2021

Published in: SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2007.03814

zbMATH Keywords

Rényi divergencevariational representationneural network estimator

Mathematics Subject Classification ID

Nonparametric estimation (62G05) Pattern recognition, speech recognition (68T10) Measures of information, entropy (94A17) Statistical aspects of information-theoretic topics (62B10)

Related Items (2)

Model Uncertainty and Correctability for Directed Graphical Models ⋮ Unnamed Item

Uses Software

• Adam
• Wasserstein GAN
• f-GAN

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Accelerated gradient methods for nonconvex nonlinear and stochastic programming
• Rényi divergence measures for commonly used univariate continuous distributions
• On variational expressions for quantum relative entropies
• Introduction to rare event simulation.
• Optimal transport for applied mathematicians. Calculus of variations, PDEs, and modeling
• Sensitivity analysis for rare events based on Rényi divergence
• The $f$-Sensitivity Index
• Equitability, mutual information, and the maximal information coefficient
• Rényi Divergence and Kullback-Leibler Divergence
• Robust Bounds on Risk-Sensitive Functionals via Rényi Divergence
• On Divergences and Informations in Statistics and Information Theory
• Rare Event Simulation using Monte Carlo Methods
• Asymptotic evaluation of certain markov process expectations for large time. IV
• High-Dimensional Probability
• Estimation of Entropy and Mutual Information
• Uniform Central Limit Theorems
• Estimating Divergence Functionals and the Likelihood Ratio by Convex Risk Minimization
• Analysis and Approximation of Rare Events
• Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming
• Approximation by superpositions of a sigmoidal function

This page was built for publication: Variational Representations and Neural Network Estimation of Rényi Divergences