AI RESEARCH

Learning Theory of the SVRG: Generalization and Convergence Analysis

arXiv CS.AI

ArXi:2605.28513v1 Announce Type: cross Variance reduction (VR) methods employ stochastic gradients with decreasing variance, and they have been widely applied to solve large-scale optimization problems in machine learning because of their efficiency. Existing theoretical studies of VR methods are mainly focused on the convergence analysis, leaving the generalization behavior largely unexplored.