Summary: Generalization Error Bounds for Collaborative
Prediction with Low-Rank Matrices
Nathan Srebro
Department of Computer Science
University of Toronto
Toronto, ON, Canada
nati@cs.toronto.edu
Noga Alon
School of Mathematical Sciences
Tel Aviv University
Ramat Aviv, Israel
nogaa@tau.ac.il
Tommi S. Jaakkola
Computer Science and Artificial Intelligence Laboratory
Massachusetts Institute of Technology
Cambridge, MA, USA
tommi@csail.mit.edu
Abstract
We prove generalization error bounds for predicting entries in a partially
observed matrix by fitting the observed entries with a low-rank matrix. In

Source: Alon, Noga - School of Mathematical Sciences, Tel Aviv University
Jaakkola, Tommi S. - Computer Science and Artificial Intelligence Laboratory & Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology (MIT)
Srebro, Nathan - Toyota Technological Institute at Chicago

Collections: Computer Technologies and Information Sciences; Mathematics