AI RESEARCH
Breaking the Stochasticity Barrier: An Adaptive Variance-Reduced Method for Variational Inequalities
arXiv CS.LG
•
ArXi:2601.23034v1 Announce Type: cross Stochastic non-convex non-concave optimization, formally characterized as Stochastic Variational Inequalities (SVIs), presents unique challenges due to rotational dynamics and the absence of a global merit function. While adaptive step-size methods (like Armijo line-search) have revolutionized convex minimization, their application to this setting is hindered by the Stochasticity Barrier: the noise in gradient estimation masks the true operator curvature, triggering erroneously large steps that destabilize convergence.