Empirical Risk Minimization with Relative Entropy Regularization: Optimality and Sensitivity Analysis

Samir M. Perlaza; Gaetan Bisson; Iñaki Esnaola; Alain Jean‐Marie; Stefano Rini

doi:10.1109/isit50566.2022.9834273

ScienceGate Book Chapters

JOURNAL ARTICLE

Empirical Risk Minimization with Relative Entropy Regularization: Optimality and Sensitivity Analysis

Samir M. Perlaza Gaetan Bisson Iñaki Esnaola Alain Jean‐Marie Stefano Rini

Year: 2022 Journal: 2022 IEEE International Symposium on Information Theory (ISIT) Pages: 684-689

DOI: 10.1109/isit50566.2022.9834273

Get Full-Text PDF Get Analytical Report

Abstract

International audience

Keywords:

Mathematics Regularization (linguistics) Empirical risk minimization Entropy (arrow of time) Applied mathematics Mathematical optimization Bounded function Probability measure Risk measure Kullback–Leibler divergence Minification Upper and lower bounds Computer science Statistics Mathematical analysis Artificial intelligence

Metrics

Cited By

4.70

FWCI (Field Weighted Citation Impact)

Refs

0.97

Citation Normalized Percentile

Is in top 1%

Is in top 10%

Citation History

Topics

Probabilistic and Robust Engineering Design

Social Sciences → Decision Sciences → Statistics, Probability and Uncertainty

Sparse and Compressive Sensing Techniques

Physical Sciences → Engineering → Computational Mechanics

Statistical Methods and Inference

Physical Sciences → Mathematics → Statistics and Probability

Empirical Risk Minimization with Relative Entropy Regularization: Optimality and Sensitivity Analysis

Abstract

Metrics

Citation History

Topics

Related Documents

Empirical Risk Minimization With Relative Entropy Regularization

Analysis of the Relative Entropy Asymmetry in the Regularization of Empirical Risk Minimization

Asymmetry of the Relative Entropy in the Regularization of Empirical Risk Minimization

On optimality of empirical risk minimization in linear aggregation

A Distributed Quasi-Newton Algorithm for Empirical Risk Minimization with Nonsmooth Regularization