Estimating Divergence Functionals and the Likelihood Ratio by Convex Risk Minimization

DOI10.1109/TIT.2010.2068870zbMATH Open1366.62071arXiv0809.0853MaRDI QIDQ5281236FDOQ5281236

Authors: Xuanlong Nguyen, Martin J. Wainwright, Michael Jordan 

Publication date: 27 July 2017

Published in: IEEE Transactions on Information Theory (Search for Journal in Brave)

Abstract: We develop and analyze $M$-estimation methods for divergence functionals and the likelihood ratios of two probability distributions. Our method is based on a non-asymptotic variational characterization of $f$-divergences, which allows the problem of estimating divergences to be tackled via convex empirical risk optimization. The resulting estimators are simple to implement, requiring only the solution of standard convex programs. We present an analysis of consistency and convergence for these estimators. Given conditions only on the ratios of densities, we show that our estimators can achieve optimal minimax rates for the likelihood ratio and the divergence functionals in certain regimes. We derive an efficient optimization algorithm for computing our estimates, and illustrate their convergence behavior and practical viability by simulations.

Full work available at URL: https://arxiv.org/abs/0809.0853

Mathematics Subject Classification ID

Nonparametric estimation (62G05) Nonparametric regression and quantile regression (62G08) Asymptotic properties of nonparametric inference (62G20) Convex programming (90C25)

Cited In (56)

• Direct density-ratio estimation with dimensionality reduction via least-squares hetero-distributional subspace search
• Formulation and properties of a divergence used to compare probability measures without absolute continuity
• Direct Learning of Sparse Changes in Markov Networks by Density Ratio Estimation
• Geometry of EM and related iterative algorithms
• On distributionally robust extreme value analysis
• Solving inverse stochastic problems from discrete particle observations using the Fokker-Planck equation and physics-informed neural networks
• On the empirical estimation of integral probability metrics
• Nonparametric estimation of Kullback-Leibler divergence
• Variational representations and neural network estimation of Rényi divergences
• A Deep Generative Approach to Conditional Sampling
• Non-parametric estimation of mutual information through the entropy of the linkage
• A Monte Carlo approach to quantifying model error in Bayesian parameter estimation
• Level sets semimetrics for probability measures with applications in hypothesis testing
• Change-point detection in time-series data by relative density-ratio estimation
• Robust Actuarial Risk Analysis
• Online direct density-ratio estimation applied to inlier-based outlier detection
• Relative Density-Ratio Estimation for Robust Distribution Comparison
• Statistical analysis of distance estimators with density differences and density ratios
• Minimum Divergence, Generalized Empirical Likelihoods, and Higher Order Expansions
• Statistical analysis of kernel-based least-squares density-ratio estimation
• Title not available (Why is that?)
• Convergence of latent mixing measures in finite and infinite mixture models
• Aggregated tests based on supremal divergence estimators for non-regular statistical models
• Smoothed noise contrastive mutual information neural estimation
• Computational complexity of kernel-based density-ratio estimation: a condition number analysis
• Machine learning with squared-loss mutual information
• Bias reduction and metric learning for nearest-neighbor estimation of Kullback-Leibler divergence
• Conditional density estimation with dimensionality reduction via squared-loss conditional entropy minimization
• Model Uncertainty and Correctability for Directed Graphical Models
• Semi-supervised learning of class balance under class-prior change by distribution matching
• Imitation learning as \(f\)-divergence minimization
• Probabilistic model validation for uncertain nonlinear systems
• Title not available (Why is that?)
• Density-difference estimation
• Data-driven spatiotemporal modeling for structural dynamics on irregular domains by stochastic dependency neural estimation
• Least-squares two-sample test
• Optimizing Variational Representations of Divergences and Accelerating Their Statistical Estimation
• Geometrical Insights for Implicit Generative Modeling
• Direct density derivative estimation
• Quantization and clustering with Bregman divergences
• Constructive setting for problems of density ratio estimation
• Improving bridge estimators via \(f\)-GAN
• Density-ratio matching under the Bregman divergence: a unified framework of density-ratio estimation
• Modern Bayesian experimental design
• Calibrated adversarial algorithms for generative modelling
• Sufficient dimension reduction via squared-loss mutual information estimation
• Stein variational gradient descent with learned direction
• Reducing the statistical error of generative adversarial networks using space-filling sampling
• GAT–GMM: Generative Adversarial Training for Gaussian Mixture Models
• Variational representations of annealing paths: Bregman information under monotonic embedding
• Optimal experimental design: formulations and computations
• Learning under nonstationarity: covariate shift and class-balance change
• Non-parametric two-sample tests: recent developments and prospects
• Robust Validation: Confident Predictions Even When Distributions Shift
• Variational Bayesian optimal experimental design with normalizing flows
• Adaptive joint distribution learning

This page was built for publication: Estimating Divergence Functionals and the Likelihood Ratio by Convex Risk Minimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5281236)