跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2606.11171 · v11

Bellman-sufficient Information Complexity

首次提交 2026-06-10 01:49
版本更新 2026-11-16 07:29
雷达观测 2026-11-17 17:12
arXiv ↗PDF ↗

摘要

We introduce Bellman-sufficient information complexity for minimax analysis of sequential decision problems. A Bellman-sufficient state retains the history needed for the controlled recursion; an index Y=χ(Ω)Y=χ(Ω) specifies which information the bounds charge. A log-penalized Bellman program gives the upper bound, and a Bellman--Fano comparison with an algorithm-dependent reference trajectory gives the lower bound. When admissibility, calibration, and growth conditions hold and the bounds match at a common localization scale, they yield an information-risk sandwich. UCB bounds the immediate decision loss through calibration and optimism, while AMS/EBO gives a robust relaxation of the AIR Bellman program. Our main application gives a negative answer to a widely studied form of the GP--UCB minimax-optimality question. For every 0<α<1/40<α<1/4, we construct a fixed bounded continuous kernel with minimax regret Θ(T1−α)Θ(T^{1-α}) along an infinite sequence of horizons. At those horizons, two globally calibrated GP--UCB rules incur linear regret under one fixed truth. A policy that applies action-index AMS to a predetermined finite set in each epoch attains the minimax order; EBO gives a dual interpretation. Many low-value directions inflate the global exploration multiplier even though ignoring them is inexpensive. Through the canonical RKHS feature map, the same construction gives a finite-horizon polynomial minimax gap for the specified maximal-information-calibrated LinUCB rule. A numerical experiment illustrates the mechanism.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

本站首次收录为 v11,暂无更早版本可对照。

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。

v11 · 2026-11-16 07:29 · 最新观测版本

Bellman-sufficient Information Complexity

We introduce Bellman-sufficient information complexity for minimax analysis of sequential decision problems. A Bellman-sufficient state retains the history needed for the controlled recursion; an index Y=χ(Ω)Y=χ(Ω) specifies which information the bounds charge. A log-penalized Bellman program gives the upper bound, and a Bellman--Fano comparison with an algorithm-dependent reference trajectory gives the lower bound. When admissibility, calibration, and growth conditions hold and the bounds match at a common localization scale, they yield an information-risk sandwich. UCB bounds the immediate decision loss through calibration and optimism, while AMS/EBO gives a robust relaxation of the AIR Bellman program. Our main application gives a negative answer to a widely studied form of the GP--UCB minimax-optimality question. For every 0<α<1/40<α<1/4, we construct a fixed bounded continuous kernel with minimax regret Θ(T1−α)Θ(T^{1-α}) along an infinite sequence of horizons. At those horizons, two globally calibrated GP--UCB rules incur linear regret under one fixed truth. A policy that applies action-index AMS to a predetermined finite set in each epoch attains the minimax order; EBO gives a dual interpretation. Many low-value directions inflate the global exploration multiplier even though ignoring them is inexpensive. Through the canonical RKHS feature map, the same construction gives a finite-horizon polynomial minimax gap for the specified maximal-information-calibrated LinUCB rule. A numerical experiment illustrates the mechanism.

查看此版本解读 →查看此版本原文 ↗