Pith. sign in

REVIEW 2 cited by

Provable Bregman-divergence based Methods for Nonconvex and Non-Lipschitz Problems

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 1904.09712 v1 pith:5RMO4OZA submitted 2019-04-22 math.OC cs.ITcs.LGmath.ITstat.ML

classification math.OCcs.ITcs.LGmath.ITstat.ML
keywords methodsalternatingconditionlipschitzminimizationoptimizationproblemssmooth
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

The (global) Lipschitz smoothness condition is crucial in establishing the convergence theory for most optimization methods. Unfortunately, most machine learning and signal processing problems are not Lipschitz smooth. This motivates us to generalize the concept of Lipschitz smoothness condition to the relative smoothness condition, which is satisfied by any finite-order polynomial objective function. Further, this work develops new Bregman-divergence based algorithms that are guaranteed to converge to a second-order stationary point for any relatively smooth problem. In addition, the proposed optimization methods cover both the proximal alternating minimization and the proximal alternating linearized minimization when we specialize the Bregman divergence to the Euclidian distance. Therefore, this work not only develops guaranteed optimization methods for non-Lipschitz smooth problems but also solves an open problem of showing the second-order convergence guarantees for these alternating minimization methods.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

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

  1. Multi-block Bregman proximal alternating linearized minimization and its application to orthogonal nonnegative matrix factorization

    math.OC 2019-08 conditional novelty 7.0 of 10

    A convergence-guaranteed Bregman proximal alternating linearized minimization framework for multi-block nonconvex nonsmooth problems, with closed-form updates for penalized orthogonal nonnegative matrix factorization.

  2. Second-Order KKT Guarantees for Bregman ADMM in Nonconvex and Non-Lipschitz Optimization

    math.OC 2026-06 unverdicted novelty 6.0 of 10

    Bregman ADMM achieves almost-sure second-order stationarity of limiting KKT points for nonconvex problems under two-sided relative smoothness via instability of strict-saddle fixed points.

Pith tools