arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1010.4515math.PRmath.STstat.MLstat.TH
收藏

Vapnik-Chervonenkis类的一致逼近

Uniform Approximation of Vapnik-Chervonenkis Classes

Terrence M. Adams, Andrew B. Nobel

摘要:

对概率空间中的任意可测集族,证明了(i)该族具有无穷维Vapnik-Chervonenkis(VC)维数,或(ii)对任意π> 0,存在一个有限分划π,使得每个集合的π-边界至多具有测度π.直接推论包括这样一个事实:一个有限VC维的族有有限的括号数,并且对每个遍历过程都满足一致大数定律。从这些推论,我们得出类似的结果VC主要和VC图形家庭的功能。

英文摘要:

For any family of measurable sets in a probability space, we show that either (i) the family has infinite Vapnik-Chervonenkis (VC) dimension or (ii) for every epsilon > 0 there is a finite partition pi such the pi-boundary of each set has measure at most epsilon. Immediate corollaries include the fact that a family with finite VC dimension has finite bracketing numbers, and satisfies uniform laws of large numbers for every ergodic process. From these corollaries, we derive analogous results for VC major and VC graph families of functions.

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。

↑