No-Regret Algorithms for Time-Varying Bayesian Optimization
arXiv:2102.06296
Abstract
In this paper, we consider the time-varying Bayesian optimization problem. The unknown function at each time is assumed to lie in an RKHS (reproducing kernel Hilbert space) with a bounded norm. We adopt the general variation budget model to capture the time-varying environment, and the variation is characterized by the change of the RKHS norm. We adapt the restart and sliding window mechanism to introduce two GP-UCB type algorithms: R-GP-UCB and SW-GP-UCB, respectively. We derive the first (frequentist) regret guarantee on the dynamic regret for both algorithms. Our results not only recover previous linear bandit results when a linear kernel is used, but complement the previous regret analysis of time-varying Gaussian process bandit under a Bayesian-type regularity assumption, i.e., each function is a sample from a Gaussian process.
References in corpus (8)
- Gaussian Processes and Kernel Methods: A Review on Connections and Equivalences
- Time-Varying Gaussian Process Bandit Optimization
- A Simple Approach for Non-stationary Linear Bandits
- Practical Hilbert space approximate Bayesian Gaussian processes for probabilistic programming
- On Kernelized Multi-armed Bandits
- Bayesian Optimization under Heavy-tailed Payoffs
- Local Differential Privacy for Bayesian Optimization
- An introduction to functional analysis for science and engineering