← 研踪 PaperTrailarXiv:2610.36097 · v1
Minimax-Optimal Small-Loss Bounds for Online Linear Optimisation on $\ell_p$ Balls
首次提交 2026-10-27 02:15
版本更新 2026-10-27 02:15
雷达观测 2026-10-29 00:35
摘要
We study full-information online linear optimisation on the unit $\ell_p$ ball in $\mathbb{R}^d$, for fixed $2\le p<\infty$ and losses of dual norm at most one. Let $Δ_T$ denote the cumulative loss of the best fixed action above each round's minimum. A follow-the-regularised-leader (FTRL) algorithm attains, on every loss sequence and without knowing $T$ or $Δ_T$, regret $O_p(1+\min\{Δ_T^{1-1/p},\, d^{1/2-1/p}\sqrt{Δ_T}\})$. Matching lower bounds show that this rate is minimax for each fixed $p$, and its constant $(2+o(1))p/\log p$ is optimal as $p\to\infty$ among guarantees uniform in $d$ and $T$. The algorithm uses a bounded radial regulariser and switches at most once to its quadratic augmentation. On some paths where follow-the-leader (FTL) has regret one, its regret grows with $T$. A switching extension keeps the sharp constant and also guarantees $\mathrm{Reg}_T\le 2\,\mathrm{Reg}_T^{\mathrm{FTL}}$. For i.i.d. losses whose mean has no zero coordinates, we compute the exact $\log T$ coefficient of the expected regret, which separates FTL's variance term from the bias of the regulariser.
作者备注：49 pages
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 · 2026-10-27 02:15 · 最新观测版本
Minimax-Optimal Small-Loss Bounds for Online Linear Optimisation on $\ell_p$ Balls
We study full-information online linear optimisation on the unit $\ell_p$ ball in $\mathbb{R}^d$, for fixed $2\le p<\infty$ and losses of dual norm at most one. Let $Δ_T$ denote the cumulative loss of the best fixed action above each round's minimum. A follow-the-regularised-leader (FTRL) algorithm attains, on every loss sequence and without knowing $T$ or $Δ_T$, regret $O_p(1+\min\{Δ_T^{1-1/p},\, d^{1/2-1/p}\sqrt{Δ_T}\})$. Matching lower bounds show that this rate is minimax for each fixed $p$, and its constant $(2+o(1))p/\log p$ is optimal as $p\to\infty$ among guarantees uniform in $d$ and $T$. The algorithm uses a bounded radial regulariser and switches at most once to its quadratic augmentation. On some paths where follow-the-leader (FTL) has regret one, its regret grows with $T$. A switching extension keeps the sharp constant and also guarantees $\mathrm{Reg}_T\le 2\,\mathrm{Reg}_T^{\mathrm{FTL}}$. For i.i.d. losses whose mean has no zero coordinates, we compute the exact $\log T$ coefficient of the expected regret, which separates FTL's variance term from the bias of the regulariser.
查看此版本解读 →查看此版本原文 ↗