Multi-task learning and algorithmic stability

Yu ZHANG*

*Corresponding author for this work

Research output: Chapter in book/report/conference proceedingConference contributionpeer-review

7 Citations (Scopus)

Abstract

In this paper, we study multi-task algorithms from the perspective of the algorithmic stability. We give a definition of the multi-task uniform stability, a generalization of the conventional uniform stability, which measures the maximum difference between the loss of a multi-task algorithm trained on a data set and that of the multitask algorithm trained on the same data set but with a data point removed in each task. In order to analyze multi-task algorithms based on multi-task uniform stability, we prove a generalized McDiarmid's inequality which assumes the difference bound condition holds by changing multiple input arguments instead of only one in the conventional McDiarmid's inequality. By using the generalized McDiarmid's inequality as a tool, we can analyze the generalization performance of general multitask algorithms in terms of the multi-task uniform stability. Moreover, as applications, we prove generalization bounds of several representative regularized multi-task algorithms.

Original languageEnglish
Title of host publicationProceedings of the 29th AAAI Conference on Artificial Intelligence, AAAI 2015 and the 27th Innovative Applications of Artificial Intelligence Conference, IAAI 2015
PublisherAI Access Foundation
Pages3181-3187
Number of pages7
ISBN (Electronic)9781577357025
ISBN (Print)9781577356981
Publication statusPublished - Jan 2015
Event29th AAAI Conference on Artificial Intelligence, AAAI 2015 and the 27th Innovative Applications of Artificial Intelligence Conference, IAAI 2015 - Austin, United States, Austin, United States
Duration: 25 Jan 201530 Jan 2015

Publication series

NameProceedings of the National Conference on Artificial Intelligence
Volume4

Conference

Conference29th AAAI Conference on Artificial Intelligence, AAAI 2015 and the 27th Innovative Applications of Artificial Intelligence Conference, IAAI 2015
Country/TerritoryUnited States
CityAustin
Period25/01/1530/01/15

Scopus Subject Areas

  • Software
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Multi-task learning and algorithmic stability'. Together they form a unique fingerprint.

Cite this