Exploring Local Norms in Exp-concave Statistical Learning

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.