Another Look at Universal Individual Learning

Yaniv Fogel, Meir Feder

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In recent papers we have proposed an individual setting for the batch learning problem and showed that it is solved by a known variant of the Normalized Maximum Likelihood (NML) which we termed pNML. In this paper we present a different possible definition for the batch learning problem in the individual setting and show that it is solved by another known variant of the normalized maximum likelihood, which we denote by pNML2. We further derive an exact expression of the pNML2 for the linear regression problem. We use this result, along with known results and new upper and lower bounds over the regret of the pNML2 learner, to compare between the two learners.

Original languageEnglish
Title of host publication2022 IEEE International Symposium on Information Theory, ISIT 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1501-1505
Number of pages5
ISBN (Electronic)9781665421591
DOIs
StatePublished - 2022
Event2022 IEEE International Symposium on Information Theory, ISIT 2022 - Espoo, Finland
Duration: 26 Jun 20221 Jul 2022

Publication series

NameIEEE International Symposium on Information Theory - Proceedings
Volume2022-June
ISSN (Print)2157-8095

Conference

Conference2022 IEEE International Symposium on Information Theory, ISIT 2022
Country/TerritoryFinland
CityEspoo
Period26/06/221/07/22

Fingerprint

Dive into the research topics of 'Another Look at Universal Individual Learning'. Together they form a unique fingerprint.

Cite this