← 研踪 PaperTrailarXiv:2611.04307 · v1
Nearly Linear-Time Follow-the-Perturbed-Leader for Weakly Observable Graph Bandits
首次提交 2026-11-03 12:38
版本更新 2026-11-03 12:38
雷达观测 2026-11-04 23:40
摘要
We study online learning with directed weakly observable feedback graphs and propose a Follow-the-Perturbed-Leader (FTPL) policy that achieves best-of-both-worlds guarantee with nearly linear expected time complexity. To preserve the simple structure of FTPL, we develop a novel graph-based loss estimator that combines forced exploration, conditional geometric resampling and adaptive learning rates with surrogate probabilities. Our policy achieves $\tilde{\mathcal{O}}(δ_*^{1/3} T^{2/3})$ regret for adversarial regimes as well as $\tilde{\mathcal{O}}(δ_* \log T / Δ_{\min}^2)$ regret for stochastic regimes, where $δ_*$ and $Δ$, respectively, denote the fractional weak domination number and the suboptimality gap. These results show that refined guarantees for problems with minimax regret of $Θ(T^{2/3})$ can be obtained through appropriately designed adaptive learning rates and loss estimators without sacrificing the simplicity of FTPL.
作者备注：preprint
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-03 12:38 · 最新观测版本
Nearly Linear-Time Follow-the-Perturbed-Leader for Weakly Observable Graph Bandits
We study online learning with directed weakly observable feedback graphs and propose a Follow-the-Perturbed-Leader (FTPL) policy that achieves best-of-both-worlds guarantee with nearly linear expected time complexity. To preserve the simple structure of FTPL, we develop a novel graph-based loss estimator that combines forced exploration, conditional geometric resampling and adaptive learning rates with surrogate probabilities. Our policy achieves $\tilde{\mathcal{O}}(δ_*^{1/3} T^{2/3})$ regret for adversarial regimes as well as $\tilde{\mathcal{O}}(δ_* \log T / Δ_{\min}^2)$ regret for stochastic regimes, where $δ_*$ and $Δ$, respectively, denote the fractional weak domination number and the suboptimality gap. These results show that refined guarantees for problems with minimax regret of $Θ(T^{2/3})$ can be obtained through appropriately designed adaptive learning rates and loss estimators without sacrificing the simplicity of FTPL.
查看此版本解读 →查看此版本原文 ↗