Derivative-Free & Order-Robust Optimisation

[edit]

Haitham Ammar, Victor Gabillon, Rasul Tutunov, Michal Valko ;
Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics, PMLR 108:2293-2303, 2020.

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.

Related Material