Learning with convex constraints

Authors:
Marco Gori;Stefano Melacci
Affiliations:
DII, University of Siena, Siena, Italy;DII, University of Siena, Siena, Italy
Venue:
ICANN'10 Proceedings of the 20th international conference on Artificial neural networks: Part III
Year:
2010

Citing 4
Cited 0

The connection between regularization operators and support vector kernels

Neural Networks
A Theory of Networks for Approximation and Learning

A Theory of Networks for Approximation and Learning
Learning Multiple Tasks with Kernel Methods

The Journal of Machine Learning Research
Letter to the editor: Semantic-based regularization and Piaget's cognitive stages

Neural Networks

Quantified Score

Hi-index	0.00

Visualization

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.