Probabilistic n-Choose-k Models for Classification and Ranking
View/ Open
Metadata
Show full item recordCitation
Swersky, Kevin, Daniel Tarlow, Ryan Prescott Adams, Richard S. Zemel, and Brendan Frey. Probabilistic n-choose-k models for classification and ranking. Advances in Neural Information Processing Systems 25: 3059-3067.Abstract
In categorical data there is often structure in the number of variables that take on each label. For example, the total number of objects in an image and the number of highly relevant documents per query in web search both tend to follow a structured distribution. In this paper, we study a probabilistic model that explicitly includes a prior distribution over such counts, along with a count-conditional likelihood that defines probabilities over all subsets of a given size. When labels are binary and the prior over counts is a Poisson-Binomial distribution, a standard logistic regression model is recovered, but for other count distributions, such priors induce global dependencies and combinatorics that appear to complicate learning and inference. However, we demonstrate that simple, efficient learning procedures can be derived for more general forms of this model. We illustrate the utility of the formulation by exploring applications to multi-object classification, learning to rank, and top-K classification.Other Sources
http://books.nips.cc/papers/files/nips25/NIPS2012_1402.txthttp://books.nips.cc/papers/files/nips25/NIPS2012_1402.pdf
Terms of Use
This article is made available under the terms and conditions applicable to Open Access Policy Articles, as set forth at http://nrs.harvard.edu/urn-3:HUL.InstRepos:dash.current.terms-of-use#OAPCitable link to this page
http://nrs.harvard.edu/urn-3:HUL.InstRepos:11223540
Collections
- FAS Scholarly Articles [18256]
Contact administrator regarding this item (to report mistakes or request changes)