Timezone: »

On Multilabel Classification and Ranking with Partial Feedback
Claudio Gentile · Francesco Orabona

Thu Dec 06 02:00 PM -- 12:00 AM (PST) @ Harrah’s Special Events Center 2nd Floor #None
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 $O(T^{1/2}\log T)$ 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.

Author Information

Claudio Gentile (INRIA)
Francesco Orabona (Boston University)

More from the Same Authors