Mathematical Programming Computation, Volume 5, Issue 2, June 2013
Parallel stochastic gradient algorithms for large-scale matrix completion
Benjamin Recht, Christopher Ré
This paper develops Jellyfish, an algorithm for solving data-processing problems with matrix-valued decision variables regularized to have low rank. Particular examples of problems solvable by Jellyfish include matrix completion problems and least-squares problems regularized by the nuclear norm or ?2-norm. Jellyfish implements a projected incremental gradient method with a biased, random ordering of the increments. This biased ordering allows for a parallel implementation that admits a speed-up nearly proportional to the number of processors. On large-scale matrix completion tasks, Jellyfish is orders of magnitude more efficient than existing codes. For example, on the Netflix Prize data set, prior art computes rating predictions in approximately 4 h, while Jellyfish solves the same problem in under 3 min on a 12 core workstation.
Full Text: PDF
Imprint and privacy statement
For the imprint and privacy statement we refer to the Imprint of ZIB.
© 2008-2020 by Zuse Institute Berlin (ZIB).