并行高斯过程乐队优化的改进遗憾分析
Improved Regret Analysis for Parallel Gaussian Process Bandit Optimization
浏览论文内容
中文总结 AI 辅助
本文针对并行GP乐队优化，改进了GP-BTS的遗憾分析，无需初始不确定性采样即可获得不含批量大小乘性因子的遗憾上界，且无噪声设置下性能更优。
中文摘要 AI 辅助
本文研究并行高斯过程（GP）乐队优化的遗憾分析。广泛使用的GP批量上置信界和GP批量汤普森采样（GP-BTS）的已知遗憾上界存在与批量大小$Q$相关的乘性因子。为避免这种性能下降，现有分析要求在优化开始时对$Q$进行多项式数量的不确定性采样（US）。然而，这种初始US阶段在实践中通常效果不佳。本文以GP-BTS为例，证明无需初始US阶段即可实现不含与$Q$相关乘性因子的遗憾上界。此外，我们表明在无噪声设置下的遗憾上界比有噪声设置下的好得多，这与顺序GP乐队设置中的情况一致。
英文摘要
This paper studies the regret analysis for parallel Gaussian process (GP) bandit optimization. The known regret upper bounds for the widely used GP batched upper confidence bound and GP batched Thompson sampling (GP-BTS) suffer from a multiplicative factor with respect to the batch size $Q$. To avoid this degradation, existing analyses require a polynomial number of uncertainty sampling (US) for $Q$ at the beginning of optimization. However, this initial US phase is often ineffective in practice. This paper shows that the regret upper bound without the multiplicative factor on $Q$ can be achieved without the initial US phase, using GP-BTS as an example. Furthermore, we show much better regret upper bounds in the noiseless setting than in the noisy setting, as in the sequential GP bandit setting.
发表机构
- Nagoya University（名古屋大学）
- MI-6 Ltd.（MI-6有限公司）
机构由 AI 辅助整理，请以论文原文为准。
