arXiv · 2611.20318
Near-Optimal Methods for Generalized Lipschitz Convex Optimization
Abstract
In this paper, we consider a convex optimization problem, where the upper bound on the subgradient norm depends on the objective function. We establish a lower bound on the number of iterations required by any first-order method to find an approximate solution to the problem. Furthermore, we present two near-optimal algorithms that can match the lower bound up to logarithmic factors. The first algorithm is a projected GD with a carefully designed stepsize schedule which incorporates warm-up and decay phases. The second algorithm is scalar-stepsize clipped AdamW which extends the near-optimal guarantees to the stochastic setting, where only a noisy unbiased estimator of the subgradient is available.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Dmitry Kovalev, Grigory Malinovsky. 2026-11-15. Near-Optimal Methods for Generalized Lipschitz Convex Optimization. https://searcharxiv.com/abs/2611.20318
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.