Derivative-Free & Order-Robust Optimisation
arXiv:1910.04034
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.
References in corpus (8)
- Overcoming catastrophic forgetting in neural networks
- Empirical Bernstein Bounds and Sample Variance Penalization
- Bandit Algorithms for Tree Search
- Stochastic simultaneous optimistic optimization
- Black-box optimization of noisy functions with unknown smoothness
- Exponential Regret Bounds for Gaussian Process Bandits with Deterministic Observations
- Online Stochastic Optimization under Correlated Bandit Feedback
- Scalable and Order-robust Continual Learning with Additive Parameter Decomposition