Convex Learning with Invariances

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 algorithms for kernels, including solvers of the SVMStruct family. The advantage of our setting is that it relies on column generation instead of modifying the underlying optimization problem directly.

• Type: Conference
• Year: 2007
• Where: NIPS
• Authors: Choon Hui Teo, Amir Globerson, Sam T. Roweis, Alex J. Smola
• Keywords: Arbitrary Loss Functions, Arbitrary Losses, Convex Formulation, Information Technology, NIPS 2007