Optimal exponential bounds for aggregation of density estimators
From MaRDI portal
(Redirected from Publication:502865)
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 -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.
The paper studies the problem of estimating an unknown density function based on observations. It shows that two classical estimators, the exponential weights aggregate and the empirical risk minimization are suboptimal in deviation. It then defines a penalized procedure based on which a sharp oracle inequality in deviation is derived, which achieves an optimal rate in deviation. Finally, the paper provides a lower bound that shows that neither the achieved rate nor the deviation term can be further improved.
Recommendations
Cited in
(13)- Optimal Kullback-Leibler aggregation in mixture density estimation by maximum likelihood
- Optimal bounds for aggregation of affine estimators
- A minimax framework for quantifying risk-fairness trade-off in regression
- Localized Gaussian width of \(M\)-convex hulls with applications to Lasso and convex aggregation
- Optimal exponential bounds for aggregation of estimators for the Kullback-Leibler loss
- scientific article; zbMATH DE number 5957353 (Why is no real title available?)
- Aggregation of spectral density estimators
- A unified scheme for generalizing cardinality estimators to sum aggregation
- A combined strategy for multivariate density estimation
- Aggregation by Exponential Weighting and Sharp Oracle Inequalities
- Simple proof of the risk bound for denoising by exponential weights for asymmetric noise distributions
- Deviation optimal learning using greedy \(Q\)-aggregation
- Linear and convex aggregation of density estimators
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)
