In this paper, we focus on multitask learning and discuss the notion of learning from constraints, in which they limit the space of admissible real values of the task functions. We formulate learning as a variational problem and analyze convex constraints, with special attention to the case of linear bilateral and unilateral constraints. Interestingly, we show that the solution is not always an analytic function and that it cannot be expressed by the classic kernel expansion on the training examples. We provide exact and approximate solutions and report experimental evidence of the improvement with respect to classic kernel machines.

Gori, M., & Melacci, S. (2010). Learning with convex constraints. In Artificial Neural Networks - ICANN 2010 (pp.315-320). Berlin : Springer Verlag [10.1007/978-3-642-15825-4_41].

Learning with convex constraints

GORI, MARCO;MELACCI, STEFANO
2010

Abstract

In this paper, we focus on multitask learning and discuss the notion of learning from constraints, in which they limit the space of admissible real values of the task functions. We formulate learning as a variational problem and analyze convex constraints, with special attention to the case of linear bilateral and unilateral constraints. Interestingly, we show that the solution is not always an analytic function and that it cannot be expressed by the classic kernel expansion on the training examples. We provide exact and approximate solutions and report experimental evidence of the improvement with respect to classic kernel machines.
978-3-642-15824-7
Gori, M., & Melacci, S. (2010). Learning with convex constraints. In Artificial Neural Networks - ICANN 2010 (pp.315-320). Berlin : Springer Verlag [10.1007/978-3-642-15825-4_41].
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11365/5958
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo