Practical Large-Scale Optimization for Max-norm Regularization

  title={Practical Large-Scale Optimization for Max-norm Regularization},
  author={Jason D. Lee and Benjamin Recht and Ruslan Salakhutdinov and Nathan Srebro and Joel A. Tropp},
The max-norm was proposed as a convex matrix regularizer in [1] and was shown to be empirically superior to the trace-norm for collaborative filtering problems. Although the max-norm can be computed in polynomial time, there are currently no practical algorithms for solving large-scale optimization problems that incorporate the max-norm. The present work uses a factorization technique of Burer and Monteiro [2] to devise scalable first-order algorithms for convex programs involving the max-norm… CONTINUE READING
Highly Cited
This paper has 109 citations. REVIEW CITATIONS


Publications citing this paper.

110 Citations

Citations per Year
Semantic Scholar estimates that this publication has 110 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.

Similar Papers

Loading similar papers…