Paper recorded by Signals 4 on 2026-10-30 in cs.LG. Abstract reproduced from arXiv; link to the original below.
Published 2026-10-30 on arXiv · recorded by Signals 4 on 2026-11-02
Category: cs.LG · 机器学习 · first seen 2026-11-02
Instance-dependent limits for bandit regret, sequential tests, best-arm identification and Markov decision processes are proved by one chain. It runs from a divergence decomposition through data processing to a statistic, a testing step that turns a class guarantee into a requirement on the history, and optimization over alternatives and allocations. Only the first step is an identity. This work w