On multilabel classification and ranking with bandit feedback

Claudio Gentile, Francesco Orabona

Research output: Contribution to journalArticlepeer-review

11 Scopus citations


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 diverse real-world multilabel data sets, often obtaining comparable performance. © 2014 Claudio Gentile and Francesco Orabona.
Original languageEnglish (US)
Pages (from-to)2451-2487
Number of pages37
JournalJournal of Machine Learning Research
StatePublished - Jan 1 2014
Externally publishedYes

Bibliographical note

Generated from Scopus record by KAUST IRTS on 2023-09-25

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software
  • Statistics and Probability
  • Control and Systems Engineering


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

Cite this