Pith. sign in

REVIEW 1 cited by

Escaping Saddle Points for Nonsmooth Weakly Convex Functions via Perturbed Proximal Algorithms

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 2102.02837 v3 pith:OGDRFWWG submitted 2021-02-04 cs.LG math.OC

classification cs.LGmath.OC
keywords perturbedproximalfunctionsnonsmoothalgorithmsconvexepsilonweakly
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

We propose perturbed proximal algorithms that can provably escape strict saddles for nonsmooth weakly convex functions. The main results are based on a novel characterization of $\epsilon$-approximate local minimum for nonsmooth functions, and recent developments on perturbed gradient methods for escaping saddle points for smooth problems. Specifically, we show that under standard assumptions, the perturbed proximal point, perturbed proximal gradient and perturbed proximal linear algorithms find $\epsilon$-approximate local minimum for nonsmooth weakly convex functions in $O(\epsilon^{-2}\log(d)^4)$ iterations, where $d$ is the dimension of the problem.

Discussion (0). Continue with ORCID 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. A Gaussian smoothing-based zeroth-order method for Goldstein second-order stationarity

    math.OC 2026-07 conditional novelty 6.0 of 10

    Introduces the Goldstein second-order δ-subdifferential for C¹,¹ functions and a Gaussian-smoothing cubic-regularization zeroth-order method that provably finds (ε₁, ε₂, δ)-second-order stationary points under a coerc...

Pith tools