Optimal exponential bounds for aggregation of density estimators

DOI10.3150/15-BEJ742MaRDI QIDQ502865zbMATH OpenOpenAlexWikidataFDO

Authors Pierre C. Bellec

Publication date 11 January 2017

Published in Bernoulli (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1405.3907, https://projecteuclid.org/euclid.bj/1475001354

zbMATH Keywords

density estimatorssharp oracle inequality

Mathematics Subject Classification ID

Density estimation (62G07) Nonparametric regression and quantile regression (62G08)

Abstract: We consider the problem of model selection type aggregation in the context of density estimation. We first show that empirical risk minimization is sub-optimal for this problem and it shares this property with the exponential weights aggregate, empirical risk minimization over the convex hull of the dictionary functions, and all selectors. Using a penalty inspired by recent works on the $Q$-aggregation procedure, we derive a sharp oracle inequality in deviation under a simple boundedness assumption and we show that the rate is optimal in a minimax sense. Unlike the procedures based on exponential weights, this estimator is fully adaptive under the uniform prior. In particular, its construction does not rely on the sup-norm of the unknown density. By providing lower bounds with exponential tails, we show that the deviation term appearing in the sharp oracle inequalities cannot be improved.

Recommendations

• Optimal exponential bounds for aggregation of estimators for the Kullback-Leibler loss
• scientific article
• Linear and convex aggregation of density estimators
• Learning Theory and Kernel Machines
• Aggregation by Exponential Weighting and Sharp Oracle Inequalities

Cited in

(13)

• Aggregation of spectral density estimators
• A combined strategy for multivariate density estimation
• Aggregation by Exponential Weighting and Sharp Oracle Inequalities
• Optimal exponential bounds for aggregation of estimators for the Kullback-Leibler loss
• Deviation optimal learning using greedy \(Q\)-aggregation
• Simple proof of the risk bound for denoising by exponential weights for asymmetric noise distributions
• Localized Gaussian width of \(M\)-convex hulls with applications to Lasso and convex aggregation
• Optimal Kullback-Leibler aggregation in mixture density estimation by maximum likelihood
• Linear and convex aggregation of density estimators
• Optimal bounds for aggregation of affine estimators
• A unified scheme for generalizing cardinality estimators to sum aggregation
• scientific article; zbMATH DE number 5957353 (Why is no real title available?)
• A minimax framework for quantifying risk-fairness trade-off in regression

This page was built for publication: Optimal exponential bounds for aggregation of density estimators

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q502865)