Online Non-Convex Learning: Following the Perturbed Leader is Optimal
- Carnegie Mellon University（卡内基梅隆大学）
- Microsoft Research, India（微软研究院（印度））
机构由 AI 辅助整理，请以论文原文为准。
更新
英文摘要：
We study the problem of online learning with non-convex losses, where the learner has access to an offline optimization oracle. We show that the classical Follow the Perturbed Leader (FTPL) algorithm achieves optimal regret rate of $O(T^{-1/2})$ in this setting. This improves upon the previous best-known regret rate of $O(T^{-1/3})$ for FTPL. We further show that an optimistic variant of FTPL achieves better regret bounds when the sequence of losses encountered by the learner is `predictable'.
