@inproceedings{gabillon2020derivative-free,
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.},
author = {Gabillon, Victor and Tutunov, Rasul and Ammar, Haitham Bou and Valko, Michal},
booktitle = {International Conference on Artificial Intelligence and Statistics},
title = {{Derivative-free {\&} order-robust optimisation}},
year = {2020}
}