AI RESEARCH
Shuffling the Stochastic Mirror Descent via Dual Lipschitz Continuity and Kernel Conditioning
arXiv CS.LG
•
ArXi:2603.16042v1 Announce Type: cross The global Lipschitz smoothness condition underlies most convergence and complexity analyses via two key consequences: the descent lemma and the gradient Lipschitz continuity. How to study the performance of optimization algorithms in the absence of Lipschitz smoothness remains an active area. The relative smoothness framework from Bauschke-Bolte-Teboulle and Lu-Freund-Nestero provides an extended descent lemma, ensuring convergence of Bregman-based proximal gradient methods and their vanilla stochastic counterparts.