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.
翻译:在本文中, 我们考虑不同时间的 Bayesian 优化问题。 每一次未知的功能都假定在有约束规范的 RKHS( 复制核心 Hilbert 空间) 中。 我们采用了通用变换预算模型来捕捉时间变化的环境, 变化的特点是 RKHS 规范的变化。 我们调整了重新启动和滑动窗口机制来引入两种 GP- UCB 类型算法: R- GP- UCB 和 SW- GP- UCB 。 我们从两种算法的动态遗憾中获得了第一个( 反复) 。 我们的结果不仅在使用线性内核时回收了先前的线性波段结果, 而且还补充了先前在Bayesian 常规假设下对时间变化的 Gaussian 进程波段所作的遗憾分析, 也就是说, 每个函数都是来自 Gausian 过程的样本 。