# Zeroth-Order Methods for Stochastic Nonconvex Nonsmooth Composite Optimization

arXiv: https://arxiv.org/abs/2510.04446 · HTML: https://mlsanity.com/paper/2510.04446/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Oct 2025.

## Built on by (most cited first, 2 of 2)

- [Composite Online-to-Nonconvex Conversion with Optimal Oracle Complexity](https://mlsanity.com/paper/2610.12328/) (2026)
- [Optimal Algorithms for Nonsmooth Nonconvex Stochastic Optimization with Constraints](https://mlsanity.com/paper/2610.13787/) (2026)

## Abstract (arXiv)

This work aims to solve a stochastic nonconvex nonsmooth composite optimization problem. Previous works on composite optimization problem requires the major part to satisfy Lipschitz smoothness or some relaxed smoothness conditions, which excludes some machine learning examples such as regularized ReLU network and sparse support matrix machine. In this work, we focus on stochastic nonconvex composite optimization problem without any smoothness assumptions. In particular, we propose two new notions of approximate stationary points for such optimization problem and obtain finite-time convergence results of two zeroth-order algorithms to these two approximate stationary points respectively. Finally, we demonstrate that these algorithms are effective using numerical experiments.