Year: 2007
Type: book-chapter
Abstract: We consider the problem of learning accurate models from multiple sources of"nearby " data. Given distinct samples from multiple data sources and estimates of the dissimilarities between these sources, we provide a general theory of whichsamples should be used to learn models for each source. This theory is applicable in a broad decision-theoretic learning framework, and yields results for classifi-cation and regression generally, and for density estimation within the exponential family. A key component of our approach is the development of approximatetriangle inequalities for expected loss, which may be of independent interest.
Source: The MIT Press eBooks
Authors: Koby Crammer, Michael Kearns, Jennifer Wortman
Institution: University of Pennsylvania
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2142604614
