Kullback-Leibler aggregation and misspecified generalized linear models

DOI10.1214/11-AOS961zbMath1274.62298arXiv0911.2919OpenAlexW3101662356MaRDI QIDQ447818

Philippe Rigollet

Publication date: 29 August 2012

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

Full work available at URL: https://arxiv.org/abs/0911.2919

zbMATH Keywords

classificationaggregationfinite sample boundslogistic regressionregressiongeneralized linear modelsoracle inequalitiesminimax lower bounds

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Point estimation (62F10) Generalized linear models (logistic models) (62J12) Learning and adaptive systems in artificial intelligence (68T05)

Related Items

Elastic-net Regularized High-dimensional Negative Binomial Regression: Consistency and Weak Signal Detection ⋮ Entropic optimal transport is maximum-likelihood deconvolution ⋮ Unnamed Item ⋮ Generalized aggregation of misspecified models: with an application to asset pricing ⋮ Minimax rates for conditional density estimation via empirical entropy ⋮ Sharp oracle inequalities for aggregation of affine estimators ⋮ An adaptive multiclass nearest neighbor classifier ⋮ Empirical risk minimization is optimal for the convex aggregation problem ⋮ Kullback-Leibler aggregation and misspecified generalized linear models ⋮ Mixture of Gaussian regressions model with logistic weights, a penalized maximum likelihood approach ⋮ Aggregation of affine estimators ⋮ Optimal learning with \textit{Q}-aggregation ⋮ Optimal Kullback-Leibler aggregation in mixture density estimation by maximum likelihood ⋮ Law of iterated logarithm and model selection consistency for generalized linear models with independent and dependent responses ⋮ Optimal bounds for aggregation of affine estimators ⋮ Deviation optimal learning using greedy \(Q\)-aggregation ⋮ Optimal learning with Bernstein Online Aggregation ⋮ Sparse estimation by exponential weighting ⋮ Graphical-model based high dimensional generalized linear models ⋮ Concentration Inequalities for Statistical Inference ⋮ Second-order Stein: SURE for SURE and other applications in high-dimensional inference ⋮ Model-averaged ℓ₁regularization using Markov chain Monte Carlo model composition ⋮ A non-asymptotic approach for model selection via penalization in high-dimensional mixture of experts models ⋮ Inference from small and big data sets with error rates ⋮ Aggregating estimates by convex optimization

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Kullback-Leibler aggregation and misspecified generalized linear models
• Exponential screening and optimal rates of sparse estimation
• Oracle inequalities in empirical risk minimization and sparse recovery problems. École d'Été de Probabilités de Saint-Flour XXXVIII-2008.
• Generalized mirror averaging and \(D\)-convex aggregation
• Linear and convex aggregation of density estimators
• Aggregation via empirical risk minimization
• Best subset selection, persistence in high-dimensional statistical learning and optimization under \(l_1\) constraint
• Concentration inequalities and model selection. Ecole d'Eté de Probabilités de Saint-Flour XXXIII -- 2003.
• Learning by mirror averaging
• Consistency and asymptotic normality of the maximum likelihood estimator in generalized linear models
• Aggregating regression procedures to improve performance
• Persistene in high-dimensional linear predictor-selection and the virtue of overparametrization
• Mixing strategies for density estimation.
• Additive logistic regression: a statistical view of boosting. (With discussion and a rejoinder by the authors)
• Functional aggregation for nonparametric regression.
• Statistical learning theory and stochastic optimization. Ecole d'Eté de Probabilitiés de Saint-Flour XXXI -- 2001.
• \(\ell _{1}\)-regularized linear regression: persistence and oracle inequalities
• Sharp oracle inequalities for aggregation of affine estimators
• General oracle inequalities for model selection
• PAC-Bayesian bounds for sparse regression estimation with exponential weights
• Empirical risk minimization is optimal for the convex aggregation problem
• Aggregation for Gaussian regression
• Simultaneous adaptation to the margin and to complexity in classification
• Spatial aggregation of local likelihood estimates with applications to classification
• Theory of Classification: a Survey of Some Recent Advances
• Robust Stochastic Approximation Approach to Stochastic Programming
• Minimax Rates of Estimation for High-Dimensional Linear Regression Over $\ell_q$-Balls
• Learning Theory and Kernel Machines
• Aggregation by Exponential Weighting and Sharp Oracle Inequalities
• Maximum Likelihood Estimation of Misspecified Models

This page was built for publication: Kullback-Leibler aggregation and misspecified generalized linear models