English

A Parameter-Free Zeroth-Order Algorithm for Decentralized Stochastic Convex Optimization

Optimization and Control 2026-03-17 v1

Abstract

We consider decentralized stochastic convex optimization on connected network, in which gradients of agents are unavailable and each agent can query only noisy function values of its own local objective. The goal is to minimize the average objective over a compact convex domain using only local two point zeroth-order oracles and peer-to-peer communication. We propose a decentralized POEM method (D-POEM) that combines symmetric two point smoothing with adaptive radius and stepsize rules, thereby avoiding prior knowledge of the Lipschitz constant and diameter. For convex Lipschitz continuous objectives, we prove an convergence rate that separates a centralized optimization term from a network disagreement term. We further conduct the numerical experiments to demonstrate POEM outperforms existing distributed zeroth-order method.

Keywords

Cite

@article{arxiv.2603.15219,
  title  = {A Parameter-Free Zeroth-Order Algorithm for Decentralized Stochastic Convex Optimization},
  author = {Jiawei Chen and Alexander Rogozin},
  journal= {arXiv preprint arXiv:2603.15219},
  year   = {2026}
}
R2 v1 2026-07-01T11:22:12.390Z