Pith. sign in

REVIEW 1 cited by

Reexamining Low Rank Matrix Factorization for Trace Norm Regularization

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1706.08934 v3 pith:S4E5MCF7 submitted 2017-06-27 cs.LG stat.ML

classification cs.LGstat.ML
keywords criticalglobalmatrixoptimizationproblemrankalgorithmallows
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Trace norm regularization is a widely used approach for learning low rank matrices. A standard optimization strategy is based on formulating the problem as one of low rank matrix factorization which, however, leads to a non-convex problem. In practice this approach works well, and it is often computationally faster than standard convex solvers such as proximal gradient methods. Nevertheless, it is not guaranteed to converge to a global optimum, and the optimization can be trapped at poor stationary points. In this paper we show that it is possible to characterize all critical points of the non-convex problem. This allows us to provide an efficient criterion to determine whether a critical point is also a global minimizer. Our analysis suggests an iterative meta-algorithm that dynamically expands the parameter space and allows the optimization to escape any non-global critical point, thereby converging to a global minimizer. The algorithm can be applied to problems such as matrix completion or multitask learning, and our analysis holds for any random initialization of the factor matrices. Finally, we confirm the good performance of the algorithm on synthetic and real datasets.

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Knowledge Graph Completion by Intermediate Variables Regularization

    cs.LG 2025-06 reject novelty 6.0 of 10

    IVR regularizer shrinks intermediate variables in tensor-decomposition KGC models and improves MRR on three benchmarks, but its stated trace-norm upper bound is false for the alpha>2 settings used by most models.

Pith tools