Multi-task classification with infinite local experts

Published

Journal Article

We propose a multi-task learning (MTL) framework for nonlinear classification, based on an infinite set of local experts in feature space. The usage of local experts enables sharing at the expert-level, encouraging the borrowing of information even if tasks are similar only in subregions of feature space. A kernel stick-breaking process (KSBP) prior is imposed on the underlying distribution of class labels, so that the number of experts is inferred in the posterior and thus model selection issues are avoided. The MTL is implemented by imposing a Dirichlet process (DP) prior on a layer above the task- dependent KSBPs. ©2009 IEEE.

Full Text

Duke Authors

Cited Authors

  • Wang, C; An, Q; Carin, L; Dunson, DB

Published Date

  • September 23, 2009

Published In

Start / End Page

  • 1569 - 1572

International Standard Serial Number (ISSN)

  • 1520-6149

Digital Object Identifier (DOI)

  • 10.1109/ICASSP.2009.4959897

Citation Source

  • Scopus