Emergent Mind
Online Learning, Stability, and Stochastic Gradient Descent
(1105.4701)
Published May 24, 2011
in
cs.LG
Abstract
In batch learning, stability together with existence and uniqueness of the solution corresponds to well-posedness of Empirical Risk Minimization (ERM) methods; recently, it was proved that CVloo stability is necessary and sufficient for generalization and consistency of ERM. In this note, we introduce CVon stability, which plays a similar note in online learning. We show that stochastic gradient descent (SDG) with the usual hypotheses is CVon stable and we then discuss the implications of CV_on stability for convergence of SGD.
We're not able to analyze this paper right now due to high demand.
Please check back later (sorry!).
Generate a summary of this paper on our Pro plan:
We ran into a problem analyzing this paper.