PAC-Bayes-empirical-Bernstein inequality

Tolstikhin, Ilya & Seldin, Yevgeny (2013) PAC-Bayes-empirical-Bernstein inequality. In Advances in Neural Information Processing Systems, 5-10 Decmber 2013, Lake Tahoe, Nevada.

View at publisher (open access)

Abstract

We present PAC-Bayes-Empirical-Bernstein inequality. The inequality is based on combination of PAC-Bayesian bounding technique with Empirical Bernstein bound. It allows to take advantage of small empirical variance and is especially useful in regression. We show that when the empirical variance is significantly smaller than the empirical loss PAC-Bayes-Empirical-Bernstein inequality is significantly tighter than PAC-Bayes-kl inequality of Seeger (2002) and otherwise it is comparable. PAC-Bayes-Empirical-Bernstein inequality is an interesting example of application of PAC-Bayesian bounding technique to self-bounding functions. We provide empirical comparison of PAC-Bayes-Empirical-Bernstein inequality with PAC-Bayes-kl inequality on a synthetic example and several UCI datasets.

Impact and interest:

6 citations in Scopus
Search Google Scholar™

Citation counts are sourced monthly from Scopus and Web of Science® citation databases.

These databases contain citations from different subsets of available publications and different time periods and thus the citation count from each is usually different. Some works are not in either database and no count is displayed. Scopus includes citations from articles published in 1996 onwards, and Web of Science® generally from 1980 onwards.

Citations counts from the Google Scholar™ indexing service can be viewed at the linked Google Scholar™ search.

Full-text downloads:

31 since deposited on 01 May 2014
8 in the past twelve months

Full-text downloads displays the total number of times this work’s files (e.g., a PDF) have been downloaded from QUT ePrints as well as the number of downloads in the previous 365 days. The count includes downloads for all files if a work has more than one.

ID Code: 70845
Item Type: Conference Paper
Refereed: Yes
Divisions: Current > QUT Faculties and Divisions > Science & Engineering Faculty
Funding:
Copyright Owner: Copyright 2013 [please consult the author]
Deposited On: 01 May 2014 01:39
Last Modified: 08 May 2014 08:06

Export: EndNote | Dublin Core | BibTeX

Repository Staff Only: item control page