TY - GEN
T1 - On multilabel classification and ranking with partial feedback
AU - Gentile, Claudio
AU - Orabona, Francesco
N1 - Generated from Scopus record by KAUST IRTS on 2023-09-25
PY - 2012/12/1
Y1 - 2012/12/1
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=84877760626&partnerID=8YFLogxK
M3 - Conference contribution
SN - 9781627480031
SP - 1151
EP - 1159
BT - Advances in Neural Information Processing Systems
ER -