Abstract | ||
---|---|---|
This contribution studies the problem of learning sparse, nonparametric models from observations drawn from an arbitrary, unknown distribution. This specific problem leads us to an algorithm extending techniques for Multiple Kernel Learning (MKL), functional ANOVA models and the Component Selection and Smoothing Operator (COSSO). The key element is to use a data-dependent regularization scheme adapting to the specific distribution underlying the data. We then present empirical evidence supporting the proposed learning algorithm. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1109/CIP.2010.5604121 | CIP |
Keywords | Field | DocType |
learning (artificial intelligence),statistical analysis,cosso,component selection and smoothing operator,data matched penalty,data-dependent regularization scheme,functional anova models,improved nonparametric sparse recovery,multiple kernel learning,nonparametric models,hafnium,learning artificial intelligence,kernel,additives,signal to noise ratio,computational mathematics,empirical evidence,analysis of variance,data models | Kernel (linear algebra),Data modeling,Pattern recognition,Computer science,Multiple kernel learning,Computational mathematics,Nonparametric statistics,Smoothing,Regularization (mathematics),Operator (computer programming),Artificial intelligence | Conference |
ISBN | Citations | PageRank |
978-1-4244-6457-9 | 0 | 0.34 |
References | Authors | |
6 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Signoretto, M. | 1 | 0 | 0.34 |
K. Pelckmans | 2 | 146 | 10.03 |
De Lathauwer, L. | 3 | 107 | 10.07 |
Johan A. K. Suykens | 4 | 635 | 53.51 |