BriefGPT.xyz
Jan, 2024
有限误差在线学习中反馈价格的界限
Bounds on the price of feedback for mistake-bounded online learning
HTML
PDF
Jesse Geneson, Linus Tang
TL;DR
改进了几种在线学习场景的最坏情况边界，包括延迟模糊强化学习、函数族组合学习、犹豫学习等，并解决了多类学习中反馈价格问题和多输入延迟模糊强化学习的边界问题。
Abstract
We improve several
worst-case bounds
for various
online learning
scenarios from (Auer and Long, Machine Learning, 1999). In particular, we sharpen an upper bound for delayed ambiguous
→