# A Zeroth-order Proximal Stochastic Gradient Method for Weakly Convex Stochastic Optimization

arXiv: https://arxiv.org/abs/2205.01633 · HTML: https://mlsanity.com/paper/2205.01633/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 May 2022.

## Built on by (most cited first, 5 of 5)

- [Differentially Private Zeroth-Order Methods for Scalable Large Language Model Finetuning](https://mlsanity.com/paper/2402.07818/) (2024)
- [Minimisation of Quasar-Convex Functions Using Random Zeroth-Order Oracles](https://mlsanity.com/paper/2505.02281/) (2025)
- [Risk-Averse Constrained Reinforcement Learning with Optimized Certainty Equivalents](https://mlsanity.com/paper/2510.20199/) (2025)
- [Explainable and Class-Revealing Signal Feature Extraction via Scattering Transform and Constrained Zeroth-Order Optimization](https://mlsanity.com/paper/2502.05722/) (2025)
- [A proximal subgradient method for nonconvex stochastic optimization under the Kurdyka-Lojasiewicz condition](https://mlsanity.com/paper/2608.05460/) (2026)

## Abstract (arXiv)

In this paper we analyze a zeroth-order proximal stochastic gradient method suitable for the minimization of weakly convex stochastic optimization problems. We consider nonsmooth and nonlinear stochastic composite problems, for which (sub-)gradient information might be unavailable. The proposed algorithm utilizes the well-known Gaussian smoothing technique, which yields unbiased zeroth-order gradient estimators of a related partially smooth surrogate problem (in which one of the two nonsmooth terms in the original problem's objective is replaced by a smooth approximation). This allows us to employ a standard proximal stochastic gradient scheme for the approximate solution of the surrogate problem, which is determined by a single smoothing parameter, and without the utilization of first-order information. We provide state-of-the-art convergence rates for the proposed zeroth-order method using minimal assumptions. The proposed scheme is numerically compared against alternative zeroth-order methods as well as a stochastic sub-gradient scheme on a standard phase retrieval problem. Further, we showcase the usefulness and effectiveness of our method for the unique setting of automated hyper-parameter tuning. In particular, we focus on automatically tuning the parameters of optimization algorithms by minimizing a novel heuristic model. The proposed approach is tested on a proximal alternating direction method of multipliers for the solution of L1/L2-regularized PDE-constrained optimal control problems, with evident empirical success.