Online optimization for max-norm regularization

Jie Shen, Huan Xu, Ping Li

Research output: Contribution to journalConference articlepeer-review

21 Scopus citations

Abstract

Max-norm regularizer has been extensively studied in the last decade as it promotes an effective low rank estimation of the underlying data. However, maxnorm regularized problems are typically formulated and solved in a batch manner, which prevents it from processing big data due to possible memory bottleneck. In this paper, we propose an online algorithm for solving max-norm regularized problems that is scalable to large problems. Particularly, we consider the matrix decomposition problem as an example, although our analysis can also be applied in other problems such as matrix completion. The key technique in our algorithm is to reformulate the max-norm into a matrix factorization form, consisting of a basis component and a coefficients one. In this way, we can solve the optimal basis and coefficients alternatively. We prove that the basis produced by our algorithm converges to a stationary point asymptotically. Experiments demonstrate encouraging results for the effectiveness and robustness of our algorithm.

Original languageEnglish
Pages (from-to)1718-1726
Number of pages9
JournalAdvances in Neural Information Processing Systems
Volume2
Issue numberJanuary
StatePublished - 2014
Event28th Annual Conference on Neural Information Processing Systems 2014, NIPS 2014 - Montreal, Canada
Duration: 8 Dec 201413 Dec 2014

Fingerprint

Dive into the research topics of 'Online optimization for max-norm regularization'. Together they form a unique fingerprint.

Cite this