{"ID":2882540,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.11073","arxiv_id":"2508.11073","title":"Zeroth-Order Non-smooth Non-convex Optimization via Gaussian Smoothing","abstract":"This paper addresses stochastic optimization of Lipschitz-continuous, nonsmooth and nonconvex objectives over compact convex sets, where only noisy function evaluations are available. While gradient-free methods have been developed for smooth nonconvex problems, extending these techniques to the nonsmooth setting remains challenging. The primary difficulty arises from the absence of a Taylor series expansion for Clarke subdifferentials, which limits the ability to approximate and analyze the behavior of the objective function in a neighborhood of a point. We propose a two time-scale zeroth-order projected stochastic subgradient method leveraging Gaussian smoothing to approximate Clarke subdifferentials. First, we establish that the expectation of the Gaussian-smoothed subgradient lies within an explicitly bounded error of the Clarke subdifferential, a result that extends prior analyses beyond convex/smooth settings. Second, we design a novel algorithm with coupled updates: a fast timescale tracks the subgradient approximation, while a slow timescale drives convergence. Using continuous-time dynamical systems theory and robust perturbation analysis, we prove that iterates converge almost surely to a neighborhood of the set of Clarke stationary points, with neighborhood size controlled by the smoothing parameter. To our knowledge, this is the first zeroth-order method achieving almost sure convergence for constrained nonsmooth nonconvex optimization problems.","short_abstract":"This paper addresses stochastic optimization of Lipschitz-continuous, nonsmooth and nonconvex objectives over compact convex sets, where only noisy function evaluations are available. While gradient-free methods have been developed for smooth nonconvex problems, extending these techniques to the nonsmooth setting remai...","url_abs":"https://arxiv.org/abs/2508.11073","url_pdf":"https://arxiv.org/pdf/2508.11073v2","authors":"[\"Anik Kumar Paul\",\"Shalabh Bhatnagar\"]","published":"2025-08-14T21:11:09Z","proceeding":"math.OC","tasks":"[\"math.OC\"]","methods":"[]","has_code":false}