Multiple source adaptation and the Rényi divergence

Yishay Mansour, Mehryar Mohri, Afshin Rostamizadeh

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


This paper presents a novel theoretical study of the general problem of multiple source adaptation using the notion of Rényi divergence. Our results build on our previous work [12], but significantly broaden the scope of that work in several directions. We extend previous multiple source loss guarantees based on distribution weighted combinations to arbitrary target distributions P, not necessarily mixtures of the source distributions, analyze both known and unknown target distribution cases, and prove a lower bound. We further extend our bounds to deal with the case where the learner receives an approximate distribution for each source instead of the exact one, and show that similar loss guarantees can be achieved depending on the divergence between the approximate and true distributions. We also analyze the case where the labeling functions of the source domains are somewhat different. Finally, we report the results of experiments with both an artificial data set and a sentiment analysis task, showing the performance benefits of the distribution weighted combinations and the quality of our bounds based on the Rényi divergence.

Original languageEnglish (US)
Title of host publicationProceedings of the 25th Conference on Uncertainty in Artificial Intelligence, UAI 2009
PublisherAUAI Press
Number of pages8
StatePublished - 2009

Publication series

NameProceedings of the 25th Conference on Uncertainty in Artificial Intelligence, UAI 2009

ASJC Scopus subject areas

  • Artificial Intelligence
  • Applied Mathematics


Dive into the research topics of 'Multiple source adaptation and the Rényi divergence'. Together they form a unique fingerprint.

Cite this