[edit]
Exploring Local Norms in Exp-concave Statistical Learning
Proceedings of Thirty Sixth Conference on Learning Theory, PMLR 195:1993-2013, 2023.
Abstract
We consider the standard 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+1/nlog(1/δ)) 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.