Home » Publication » 27082

Dettaglio pubblicazione

2018, ANALYSIS AND APPLICATIONS, Pages 1-54 (volume: 16)

Regularized learning schemes in feature Banach spaces (01a Articolo in rivista)

Combettes Pl, Salzo S, Villa S

This paper proposes a unified framework for the investigation of constrained learning theory in reflexive Banach spaces of features via regularized empirical risk minimization. The focus is placed on Tikhonov-like regularization with totally convex functions. This broad class of regularizers provides a flexible model for various priors on the features, including, in particular, hard constraints and powers of Banach norms. In such context, the main results establish a new general form of the representer theorem and the consistency of the corresponding learning schemes under general conditions on the loss function, the geometry of the feature space, and the modulus of total convexity of the regularizer. In addition, the proposed analysis gives new insight into basic tools such as reproducing Banach spaces, feature maps, and universality. Even when specialized to Hilbert spaces, this framework yields new results that extend the state of the art.
Gruppo di ricerca: Continuous Optimization
© Università degli Studi di Roma "La Sapienza" - Piazzale Aldo Moro 5, 00185 Roma