Infinite-dimensional gradient-based descent for alpha-divergence minimisation

DOI10.1214/20-AOS2035zbMath1486.62065arXiv2005.10618OpenAlexW3204854592MaRDI QIDQ2054493

François Portier, Kamélia Daudel, Randal Douc

Publication date: 3 December 2021

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2005.10618

zbMATH Keywords

Kullback-Leibler divergencevariational inferencemirror descentalpha-divergence

Mathematics Subject Classification ID

Density estimation (62G07) Parametric inference under constraints (62F30) Bayesian inference (62F15) Robustness and adaptive procedures (parametric inference) (62F35) Sequential statistical methods (62L99)

Related Items (1)

The recursive variational Gaussian approximation (R-VGA)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Families of alpha-, beta- and gamma-divergences: flexible and robust measures of similarities
• Convergence of adaptive mixtures of importance sampling schemes
• Efficiency versus robustness: The case for minimum Hellinger distance and related methods
• Mirror descent and nonlinear projected subgradient methods for convex optimization.
• Optimal global rates of convergence for nonparametric regression
• An introduction to variational methods for graphical models
• Safe adaptive importance sampling: a mixture approach
• Central limit theorem for sequential Monte Carlo methods and its application to Bayesian inference
• Rényi Divergence and Kullback-Leibler Divergence
• Large-Scale Machine Learning with Stochastic Gradient Descent
• Robust Stochastic Approximation Approach to Stochastic Programming
• Bayesian Estimates of Equation System Parameters: An Application of Integration by Monte Carlo
• Expectation Propagation in the Large Data Limit
• Prox-Method with Rate of Convergence O(1/t) for Variational Inequalities with Lipschitz Continuous Monotone Operators and Smooth Convex-Concave Saddle Point Problems
• 10.1162/jmlr.2003.3.4-5.993
• Adaptive importance sampling in monte carlo integration
• Markov Processes and the H-Theorem
• On Information and Sufficiency
• A Stochastic Approximation Method

This page was built for publication: Infinite-dimensional gradient-based descent for alpha-divergence minimisation