Mirror averaging with sparsity priors

DOI10.3150/11-BEJ361zbMath1243.62008arXiv1003.1189MaRDI QIDQ442083

Arnak S. Dalalyan, Alexandre B. Tsybakov

Publication date: 9 August 2012

Published in: Bernoulli (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1003.1189

zbMATH Keywords

oracle inequalities; aggregation of estimators; probably approximately correct Bayesian

Mathematics Subject Classification ID

62G07: Density estimation

62H30: Classification and discrimination; cluster analysis (statistical aspects)

62J05: Linear regression; mixed models

62F15: Bayesian inference

62C99: Statistical decision theory

Related Items

Adaptive Bayesian density regression for high-dimensional data, Sparse estimation by exponential weighting, Sparse regression learning by aggregation and Langevin Monte-Carlo, Exponential screening and optimal rates of sparse estimation, Entropic optimal transport is maximum-likelihood deconvolution, Optimal Kullback-Leibler aggregation in mixture density estimation by maximum likelihood, A quasi-Bayesian perspective to online clustering, On the exponentially weighted aggregate with the Laplace prior, Sharp oracle inequalities for aggregation of affine estimators, PAC-Bayesian bounds for sparse regression estimation with exponential weights, Exponential weights in multivariate regression and a low-rankness favoring prior, Prediction error bounds for linear regression with the TREX, PAC-Bayesian risk bounds for group-analysis sparse regression by exponential weighting, Optimal learning with \textit{Q}-aggregation

Uses Software

• EBayesThresh

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• The Adaptive Lasso and Its Oracle Properties
• Sparse regression learning by aggregation and Langevin Monte-Carlo
• Exponential screening and optimal rates of sparse estimation
• The Dantzig selector and sparsity oracle inequalities
• Generalized mirror averaging and \(D\)-convex aggregation
• PAC-Bayesian bounds for randomized empirical risk minimizers
• Some sharp performance bounds for least squares regression with \(L_1\) regularization
• Sparsity in penalized empirical risk minimization
• Nonlinear estimation over weak Besov spaces and minimax Bayes
• From \(\varepsilon\)-entropy to KL-entropy: analysis of minimum information complexity density estima\-tion
• The sparsity and bias of the LASSO selection in high-dimensional linear regression
• Learning by mirror averaging
• A universal procedure for aggregating estimators
• Mixing least-squares estimators when the variance is unknown
• Sparse recovery in convex hulls via entropy penalization
• PAC-Bayesian stochastic model selection
• Aggregating regression procedures to improve performance
• Statistical learning theory and stochastic optimization. Ecole d'Eté de Probabilitiés de Saint-Flour XXXI -- 2001.
• Statistical behavior and consistency of classification methods based on convex risk minimization.
• Optimal aggregation of classifiers in statistical learning.
• On the optimality of the aggregate with exponential weights for low temperatures
• Fast learning rates in statistical inference through aggregation
• Simultaneous analysis of Lasso and Dantzig selector
• High-dimensional generalized linear models and the lasso
• Sparsity oracle inequalities for the Lasso
• Recursive aggregation of estimators by the mirror descent algorithm with averaging
• Aggregation for Gaussian regression
• On optimality of Bayesian testimation in the normal means problem
• Optimal rates of aggregation in classification under low noise assumption
• The Dantzig selector: statistical estimation when \(p\) is much larger than \(n\). (With discussions and rejoinder).
• High-dimensional graphs and variable selection with the Lasso
• Empirical Bayes selection of wavelet thresholds
• Better Subset Regression Using the Nonnegative Garrote
• On the Generalization Ability of On-Line Learning Algorithms
• Stable recovery of sparse overcomplete representations in the presence of noise
• Information Theory and Mixing Least-Squares Regressions
• Smoothing of Multivariate Data
• Sequential Procedures for Aggregating Arbitrary Estimators of a Conditional Mean
• Adaptive Regression by Mixing
• Sequential prediction of individual sequences under general loss functions
• Learning Theory and Kernel Machines
• Aggregation and Sparsity Via ℓ1 Penalized Least Squares
• Regularization and Variable Selection Via the Elastic Net
• Aggregation by Exponential Weighting and Sharp Oracle Inequalities
• Prediction, Learning, and Games
• Convexity, Classification, and Risk Bounds