Generalization Error Bounds for Collaborative Prediction with Low-Rank Matrices

We prove generalization error bounds for predicting entries in a partially observed matrix by fitting the observed entries with a low-rank matrix. In justifying the analysis approach we take to obtain the bounds, we present an example of a class of functions of finite pseudodimension such that the sums of functions from this class have unbounded pseudodimension.

• Type: Conference
• Year: 2004
• Where: NIPS
• Authors: Nathan Srebro, Noga Alon, Tommi Jaakkola
• Keywords: Generalization Error Bounds, NIPS 2004, NIPS 2007, Observed Entries, Observed Matrix