Xiaoming Yuan

This paper provides a comprehensive generalization analysis of Stochastic Gradient Descent with Momentum (SGDM) by establishing tight, on-average model stability bounds that show SGDM can generalize well to unseen data.

This paper provides the first non-vacuous generalization analysis for the Stochastic Variance Reduced Gradient (SVRG) method by establishing sharp, data-dependent algorithmic stability bounds, thereby clarifying the link between optimization and generalization.