arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2005.07605stat.MLcs.LG
收藏

一般随机过程下的可学习性

On Learnability under General Stochastic Processes

A. Philip Dawid, Ambuj Tewari

摘要:

独立同分布(iid)抽样下的统计学习理论和最坏情况个体序列的在线学习理论是学习理论中发展最好的两个分支。一般非iid随机过程下的统计学习还不太成熟。我们提供了两个自然的概念下的一般随机过程的函数类的学习。我们表明,这两个概念实际上都相当于在线学习能力。我们的结果适用于二进制分类和回归。

英文摘要:

Statistical learning theory under independent and identically distributed (iid) sampling and online learning theory for worst case individual sequences are two of the best developed branches of learning theory. Statistical learning under general non-iid stochastic processes is less mature. We provide two natural notions of learnability of a function class under a general stochastic process. We show that both notions are in fact equivalent to online learnability. Our results hold for both binary classification and regression.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑