Derivative-Free Order-Robust Optimisation

10/09/2019
by   Victor Gabillon, et al.
0

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.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset