DCA for online prediction with expert advice - Université de Lorraine Accéder directement au contenu
Article Dans Une Revue Neural Computing and Applications Année : 2021

DCA for online prediction with expert advice

Résumé

We investigate DC (Difference of Convex functions) programming and DCA (DC Algorithm) for a class of online learning techniques, namely prediction with expert advice, where the learner’s prediction is made based on the weighted average of experts’ predictions. The problem of predicting the experts’ weights is formulated as a DC program for which an online version of DCA is investigated. The two so-called approximate/complete variants of online DCA based schemes are designed, and their regrets are proved to be logarithmic/sublinear. The four proposed algorithms for online prediction with expert advice are furthermore applied to online binary classification. Experimental results tested on various benchmark datasets showed their performance and their superiority over three standard online prediction with expert advice algorithms—the well-known weighted majority algorithm and two online convex optimization algorithms.
Fichier non déposé

Dates et versions

hal-03212803 , version 1 (30-04-2021)

Identifiants

Citer

Hoai An Le Thi, Vinh Thanh Ho. DCA for online prediction with expert advice. Neural Computing and Applications, 2021, 33 (15), pp.9521-9544. ⟨10.1007/s00521-021-05709-0⟩. ⟨hal-03212803⟩
61 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More