𝔖 Bobbio Scriptorium
✦   LIBER   ✦

An inequality for uniform deviations of sample averages from their means

✍ Scribed by Peter Bartlett; Gábor Lugosi

Publisher
Elsevier Science
Year
1999
Tongue
English
Weight
97 KB
Volume
44
Category
Article
ISSN
0167-7152

No coin nor oath required. For personal study only.

✦ Synopsis

We derive a new inequality for uniform deviations of averages from their means. The inequality is a common generalization of previous results of Vapnik and Chervonenkis [1974, Theory of Pattern Recognition. Nauka, Moscow] and Pollard [1995, Uniform ratio limit theorems for empirical processes, Scand. J. Statist. 22,[271][272][273][274][275][276][277][278]. Using the new inequality we obtain tight bounds for empirical loss minimization learning.

📜 SIMILAR VOLUMES

A bound on the expected maximal deviatio
A bound on the expected maximal deviation of averages from their means
✍ Michael Hamers; Michael Kohler 📂 Article 📅 2003 🏛 Elsevier Science 🌐 English ⚖ 136 KB

A bound on the expected maximal deviation of averages from their means over a ÿnite space of functions is derived. The usefulness of this new bound is demonstrated by an application in nonparametric regression.

An algorithm for the uniform sampling of
An algorithm for the uniform sampling of iso-energy surfaces and for the calculation of microcanonical averages
✍ Arnaldo Rapallo 📂 Article 📅 2006 🏛 John Wiley and Sons 🌐 English ⚖ 543 KB

## Abstract In this article an algorithm is proposed to efficiently perform the uniform sampling of an iso‐energy surface corresponding to a fixed potential energy __U__ of a molecular system, and for calculating averages of certain quantities over microstates having this energy (microcanonical ave