On multilabel classification and ranking with partial feedback

Claudio Gentile, Francesco Orabona

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

9 Scopus citations

Abstract

We present a novel multilabel/ranking algorithm working in partial information settings. The algorithm is based on 2nd-order descent methods, and relies on upper-confidence bounds to trade-off exploration and exploitation. We analyze this algorithm in a partial adversarial setting, where covariates can be adversarial, but multilabel probabilities are ruled by (generalized) linear models. We show O(T1/2 log T) regret bounds, which improve in several ways on the existing results. We test the effectiveness of our upper-confidence scheme by contrasting against full-information baselines on real-world multilabel datasets, often obtaining comparable performance.
Original languageEnglish (US)
Title of host publicationAdvances in Neural Information Processing Systems
Pages1151-1159
Number of pages9
StatePublished - Dec 1 2012
Externally publishedYes

Fingerprint

Dive into the research topics of 'On multilabel classification and ranking with partial feedback'. Together they form a unique fingerprint.

Cite this