Saved in:
Bibliographic Details
Main Author: Combes, Richard
Format: Preprint
Published: 2015
Subjects:
Online Access:https://arxiv.org/abs/1511.05240
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911861486649344
author Combes, Richard
author_facet Combes, Richard
contents We generalize McDiarmid's inequality for functions with bounded differences on a high probability set, using an extension argument. Those functions concentrate around their conditional expectations. We further extend the results to concentration in general metric spaces.
format Preprint
id arxiv_https___arxiv_org_abs_1511_05240
institution arXiv
publishDate 2015
record_format arxiv
spellingShingle An extension of McDiarmid's inequality
Combes, Richard
Machine Learning
Probability
Statistics Theory
We generalize McDiarmid's inequality for functions with bounded differences on a high probability set, using an extension argument. Those functions concentrate around their conditional expectations. We further extend the results to concentration in general metric spaces.
title An extension of McDiarmid's inequality
topic Machine Learning
Probability
Statistics Theory
url https://arxiv.org/abs/1511.05240