A One-Sided McDiarmid-Type Inequality for Heavy Tails via Reverse KL Tensorization

2026-10-16来源 arXiv stat.MLEnglish
arXiv:2610.21103v1 Announce Type: cross Abstract: We revisit McDiarmid's inequality, a central tool in statistical learning theory and algorithm analysis. We show that large deviations above the mean are exponentially unlikely for functions of independent random variables that are almost surely bounded above and satisfy a conditional moment assumption of order $p\in(1,2]$. When $p

原文：https://www.a8q9.cn/en/article/a-one-sided-mcdiarmid-type-inequality-for-heavy-tails-via-reverse-kl-tensorizati-1a21c9.html

相关文章