{"ID":2836619,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.21917","arxiv_id":"2511.21917","title":"Generalization of Silver Stepsize Schedule to Stochastic Optimization","abstract":"This work introduces a two-step stepsize schedule for stochastic gradient methods minimizing smooth strongly convex functions. We consider the setting where only stochastic gradient approximations, which are unbiased, of bounded variance, and supported on a finite set, are accessible. When the variance bound is relatively smaller than a ratio of the initial optimality gap, the proposed stepsize schedule achieves better convergence performance compared to the well-regarded constant stepsize α = 2/(M+m), where m and M denote the strong convexity and gradient-Lipschitz parameters, respectively. Our stepsize schedule can be viewed as a generalization of the well-known two-step silver stepsize schedule in [J. M. Altschuler and P. A. Parrilo, Journal of the ACM, 72(2):1-38, 2025] from deterministic setting to stochastic optimization.","short_abstract":"This work introduces a two-step stepsize schedule for stochastic gradient methods minimizing smooth strongly convex functions. We consider the setting where only stochastic gradient approximations, which are unbiased, of bounded variance, and supported on a finite set, are accessible. When the variance bound is relativ...","url_abs":"https://arxiv.org/abs/2511.21917","url_pdf":"https://arxiv.org/pdf/2511.21917v1","authors":"[\"Luwei Bai\",\"Yang Zeng\",\"Baoyu Zhou\"]","published":"2025-11-26T21:16:28Z","proceeding":"math.OC","tasks":"[\"math.OC\"]","methods":"[]","has_code":false}