2012/06/30 by Claudio Gentile, Francesco Orabona, Gentile, Claudio +1
Computer Science · #FOS: Computer and information sciences #Machine Learning (cs.LG) #cs.LG
paper · pdf · doi:10.48550/arxiv.1207.0166
arxiv created 2013/01/16 · arxiv updated 2013/01/17
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.