English

Convergence of Clipped SGD on Convex $(L_0,L_1)$-Smooth Functions

Optimization and Control 2025-06-04 v2

Abstract

We study stochastic gradient descent (SGD) with gradient clipping on convex functions under a generalized smoothness assumption called (L0,L1)(L_0,L_1)-smoothness. Using gradient clipping, we establish a high probability convergence rate that matches the SGD rate in the LL smooth case up to polylogarithmic factors and additive terms. We also propose a variation of adaptive SGD with gradient clipping, which achieves the same guarantee. We perform empirical experiments to examine our theory and algorithmic choices.

Keywords

Cite

@article{arxiv.2502.16492,
  title  = {Convergence of Clipped SGD on Convex $(L_0,L_1)$-Smooth Functions},
  author = {Ofir Gaash and Kfir Yehuda Levy and Yair Carmon},
  journal= {arXiv preprint arXiv:2502.16492},
  year   = {2025}
}