Document Type

Article

Publication Title

arXiv

Abstract

Gradient-free/zeroth-order methods for black-box convex optimization have been extensively studied in the last decade with the main focus on oracle calls complexity. In this paper, besides the oracle complexity, we focus also on iteration complexity, and propose a generic approach that, based on optimal first-order methods, allows to obtain in a black-box fashion new zeroth-order algorithms for non-smooth convex optimization problems. Our approach not only leads to optimal oracle complexity, but also allows to obtain iteration complexity similar to first-order methods, which, in turn, allows to exploit parallel computations to accelerate the convergence of our algorithms. We also elaborate on extensions for stochastic optimization problems, saddle-point problems, and distributed optimization. © 2022, CC BY.

DOI

10.48550/arXiv.2201.12289

Publication Date

1-28-2022

Keywords

Black boxes; Convex optimisation; Convex optimization problems; First order; First-order methods; Generic approach; Non-smooth convex optimizations; Optimisations; Ordering algorithms; Power

Comments

Preprint: arXiv

  • Archived with thanks to arXiv
  • Preprint License: CC by
  • Uploaded 24 March 2022

Share

COinS