Fully Adaptive Zeroth-Order Method for Minimizing Functions with Compressible Gradients
Abstract
We propose an adaptive zeroth-order method for minimizing differentiable functions with -Lipschitz continuous gradients. The method is designed to take advantage of the eventual compressibility of the gradient of the objective function, but it does not require knowledge of the approximate sparsity level or the Lipschitz constant of the gradient. We show that the new method performs no more than function evaluations to find an -approximate stationary point of an objective function with variables. Assuming additionally that the gradients of the objective function are compressible, we obtain an improved complexity bound of function evaluations, which holds with high probability. Preliminary numerical results illustrate the efficiency of the proposed method and demonstrate that it can significantly outperform its non-adaptive counterpart.
Cite
@article{arxiv.2501.11616,
title = {Fully Adaptive Zeroth-Order Method for Minimizing Functions with Compressible Gradients},
author = {Geovani Nunes Grapiglia and Daniel McKenzie},
journal= {arXiv preprint arXiv:2501.11616},
year = {2025}
}
Comments
V3: Added two new benchmark algorithms and a new sparse gradient benchmarking function