Pith. sign in

REVIEW

Perturbed Proximal Descent to Escape Saddle Points for Non-convex and Non-smooth Objective Functions

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 1901.08958 v1 pith:GTPHT3O2 submitted 2019-01-24 cs.LG math.OCstat.ML

Zhishen Huang , Stephen Becker This is my paper · ORCID
classification cs.LGmath.OCstat.ML
keywords non-smoothdifferentnon-convexpointsresultssaddlealgorithmanalysis
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We consider the problem of finding local minimizers in non-convex and non-smooth optimization. Under the assumption of strict saddle points, positive results have been derived for first-order methods. We present the first known results for the non-smooth case, which requires different analysis and a different algorithm.

Discussion (0). Continue with ORCID to comment.

Pith tools