Convex learning with invariances

Loading...
Thumbnail Image

Date

Authors

Teo, Choon-Hui
Globerson, Amir
Roweis, Sam
Smola, Alexander

Journal Title

Journal ISSN

Volume Title

Publisher

MIT Press

Abstract

Incorporating invariances into a learning algorithm is a common problem in machine learning. We provide a convex formulation which can deal with arbitrary loss functions and arbitrary losses. In addition, it is a drop-in replacement for most optimization

Description

Citation

Source

Advances in Neural Information Processing Systems 20: Proceedings of the 2007 Conference

Book Title

Entity type

Access Statement

License Rights

DOI

Restricted until

2037-12-31