math.OCNov 15, 2026

Near-Optimal Methods for Generalized Lipschitz Convex Optimization

Authors: Dmitry Kovalev, Grigory Malinovsky

Organizations: Yandex Research · King Abdullah University of Science and Technology

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.

Figures & tables

Explore similar work

CardsList
  1. New Bounds for the Last Iterate of the Stochastic subGradient Method

    Jun 23, 2026Guglielmo Beretta, Tommaso Cesari, Roberto Colomboni +1Stochastic OptimizationLast-Iterate Convergence

  2. Revisiting AdaGrad in Stochastic Convex Optimization: Last Iterates, High Probability, and Lower Bounds

    Sep 26, 2026Weiming Ou, Xiao WangConvergence AnalysisAdaptive Gradient Methods