Exploring Local Norms in Exp-concave Statistical Learning

2023/02/21 by Puchkin, Nikita, Zhivotovskiy, Nikita · 1 citation
#FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Statistics Theory (math.ST)

paper · doi:10.48550/arxiv.2302.10726

Abstract

We consider the problem of stochastic convex optimization with exp-concave losses using Empirical Risk Minimization in a convex class. Answering a question raised in several prior works, we provide a O( d / n + log( 1 / δ) / n ) excess risk bound valid for a wide class of bounded exp-concave losses, where d is the dimension of the convex reference set, n is the sample size, and δ is the confidence level. Our result is based on a unified geometric assumption on the gradient of losses and the notion of local norms.

Cited by

• Hardness, Structural Knowledge, and Opportunity: An Analytical Framework for Modular Performance Modeling

Related

• Excess Risk Bounds for Exponentially Concave Losses
• Fast rates with high probability in exp-concave statistical learning
• Characterization of Excess Risk for Locally Strongly Convex Population Risk
• A Simple Analysis for Exp-concave Empirical Minimization with Arbitrary Convex Regularizer
• Optimistic Rates for Learning with a Smooth Loss