Part of Advances in Neural Information Processing Systems 17 (NIPS 2004)
Nathan Srebro, Jason Rennie, Tommi Jaakkola
We present a novel approach to collaborative prediction, using low-norm instead of low-rank factorizations. The approach is inspired by, and has strong connections to, large-margin linear discrimination. We show how to learn low-norm factorizations by solving a semi-deﬁnite program, and discuss generalization error bounds for them.