Derivative-Free & Order-Robust Optimisation
Machine Learning
2019-10-23 v3 Machine Learning
Abstract
In this paper, we formalise order-robust optimisation as an instance of online learning minimising simple regret, and propose Vroom, a zero'th order optimisation algorithm capable of achieving vanishing regret in non-stationary environments, while recovering favorable rates under stochastic reward-generating processes. Our results are the first to target simple regret definitions in adversarial scenarios unveiling a challenge that has been rarely considered in prior work.
Cite
@article{arxiv.1910.04034,
title = {Derivative-Free & Order-Robust Optimisation},
author = {Victor Gabillon and Rasul Tutunov and Michal Valko and Haitham Bou Ammar},
journal= {arXiv preprint arXiv:1910.04034},
year = {2019}
}