English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Learning output kernels with block coordinate descent

Dinuzzo, F., Ong, C., Gehler, P., & Pillonetto, G. (2011). Learning output kernels with block coordinate descent. In L. Getoor, & T. Scheffer (Eds.), 28th International Conference on Machine Learning (ICML 2011) (pp. 49-56). Madison, WI, USA: International Machine Learning Society.

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/11858/00-001M-0000-0013-BB22-D Version Permalink: http://hdl.handle.net/21.11116/0000-0002-0A99-7
Genre: Conference Paper

Files

show Files

Locators

show
hide
Locator:
http://www.icml-2011.org/ (Table of contents)
Description:
-

Creators

show
hide
 Creators:
Dinuzzo, F1, Author              
Ong, CS, Author              
Gehler, PV, Author              
Pillonetto, G, Author
Affiliations:
1Dept. Empirical Inference, Max Planck Institute for Intelligent Systems, Max Planck Society, DE, ou_1497647              

Content

show
hide
Free keywords: -
 Abstract: We propose a method to learn simultaneously a vector-valued function and a kernel between its components. The obtained kernel can be used both to improve learning performances and to reveal structures in the output space which may be important in their own right. Our method is based on the solution of a suitable regularization problem over a reproducing kernel Hilbert space (RKHS) of vector-valued functions. Although the regularized risk functional is non-convex, we show that it is invex, implying that all local minimizers are global minimizers. We derive a block-wise coordinate descent method that efficiently exploits the structure of the objective functional. Then, we empirically demonstrate that the proposed method can improve classification accuracy. Finally, we provide a visual interpretation of the learned kernel matrix for some well known datasets.

Details

show
hide
Language(s):
 Dates: 2011-07
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Method: -
 Identifiers: BibTex Citekey: DinuzzoOGP2011
 Degree: -

Event

show
hide
Title: 28th International Conference on Machine Learning (ICML 2011)
Place of Event: Bellevue, WA, USA
Start-/End Date: -

Legal Case

show

Project information

show

Source 1

show
hide
Title: 28th International Conference on Machine Learning (ICML 2011)
Source Genre: Proceedings
 Creator(s):
Getoor, L, Editor
Scheffer, T, Editor
Affiliations:
-
Publ. Info: Madison, WI, USA : International Machine Learning Society
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 49 - 56 Identifier: ISBN: 978-1-450-30619-5