English

Asymptotic normality and optimality in nonsmooth stochastic approximation

Optimization and Control 2023-01-18 v1 Statistics Theory Machine Learning Statistics Theory

Abstract

In their seminal work, Polyak and Juditsky showed that stochastic approximation algorithms for solving smooth equations enjoy a central limit theorem. Moreover, it has since been argued that the asymptotic covariance of the method is best possible among any estimation procedure in a local minimax sense of H\'{a}jek and Le Cam. A long-standing open question in this line of work is whether similar guarantees hold for important non-smooth problems, such as stochastic nonlinear programming or stochastic variational inequalities. In this work, we show that this is indeed the case.

Keywords

Cite

@article{arxiv.2301.06632,
  title  = {Asymptotic normality and optimality in nonsmooth stochastic approximation},
  author = {Damek Davis and Dmitriy Drusvyatskiy and Liwei Jiang},
  journal= {arXiv preprint arXiv:2301.06632},
  year   = {2023}
}

Comments

The arxiv report arXiv:2108.11832 has been split into two parts. This is Part 2 of the original submission, augmented by a some new results and a reworked exposition

R2 v1 2026-06-28T08:12:55.473Z