An Upper Bound for Aggregating Algorithm for Regression with Changing Dependencies

Research output: Chapter in Book/Report/Conference proceedingConference contribution

288 Downloads (Pure)

Abstract

The paper presents a competitive prediction-style upper bound on the square loss of the Aggregating Algorithm for Regression with Changing Dependencies in the linear case. The algorithm is able to compete with a sequence of linear predictors provided the sum of squared Euclidean norms of differences of regression coefficient vectors grows at a sublinear rate.
Original languageEnglish
Title of host publicationAlgorithmic Learning Theory
Subtitle of host publication27th International Conference, ALT 2016, Bari, Italy, October 19-21, 2016, Proceedings
PublisherSpringer International Publishing
Pages238-252
Number of pages15
Volume9925
ISBN (Electronic)978-3-319-46379-7
ISBN (Print)978-3-319-46378-0
DOIs
Publication statusPublished - 2016

Publication series

NameLecture Notes in Computer Science
PublisherSpringer International Publishing
Volume9925
ISSN (Print)0302-9743

Keywords

  • on-line learning
  • prediction with expert advice
  • competitive prediction
  • linear regression

Cite this