Domain Adaptation with Multiple Sources

12 years 1 months ago
Domain Adaptation with Multiple Sources
This paper presents a theoretical analysis of the problem of domain adaptation with multiple sources. For each source domain, the distribution over the input points as well as a hypothesis with error at most are given. The problem consists of combining these hypotheses to derive a hypothesis with small error with respect to the target domain. We present several theoretical results relating to this problem. In particular, we prove that standard convex combinations of the source hypotheses may in fact perform very poorly and that, instead, combinations weighted by the source distributions benefit from favorable theoretical guarantees. Our main result shows that, remarkably, for any fixed target function, there exists a distribution weighted combining rule that has a loss of at most with respect to any target mixture of the source distributions. We further generalize the setting from a single target function to multiple consistent target functions and show the existence of a combining ...
Yishay Mansour, Mehryar Mohri, Afshin Rostamizadeh
Added 30 Oct 2010
Updated 30 Oct 2010
Type Conference
Year 2008
Where NIPS
Authors Yishay Mansour, Mehryar Mohri, Afshin Rostamizadeh
Comments (0)