Pith. sign in

REVIEW 3 cited by

Second-order methods for provably escaping strict saddle points in composite nonconvex and nonsmooth optimization

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 2506.22332 v1 pith:OQO3CPKL submitted 2025-06-27 math.OC

Second-order methods for provably escaping strict saddle points in composite nonconvex and nonsmooth optimization

classification math.OC
keywords pointssecond-ordernonsmoothcompositemethodsnonconvexoptimizationprovably
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

This study introduces two second-order methods designed to provably avoid saddle points in composite nonconvex optimization problems: (i) a nonsmooth trust-region method and (ii) a curvilinear linesearch method. These developments are grounded in the forward-backward envelope (FBE), for which we analyze the local second-order differentiability around critical points and establish a novel equivalence between its second-order stationary points and those of the original objective. We show that the proposed algorithms converge to second-order stationary points of the FBE under a mild local smoothness condition on the proximal mapping of the nonsmooth term. Notably, for \( \C^2 \)-partly smooth functions, this condition holds under a standard strict complementarity assumption. To the best of our knowledge, these are the first second-order algorithms that provably escape nonsmooth strict saddle points of composite nonconvex optimization, regardless of the initialization. Our preliminary numerical experiments show promising performance of the developed methods, validating our theoretical foundations.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 3 Pith papers

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

  1. Quasar-Convex Optimization: Fundamental Properties and High-Order Proximal-Point Methods

    math.OC 2026-04 unverdicted novelty 7.0

    Quasar-convex functions admit high-order proximal algorithms with linear convergence for p=2 and superlinear for p>2 under suitable conditions.

  2. PANOC-lite: A simpler and more efficient algorithm for composite minimization

    math.OC 2026-04 unverdicted novelty 6.0

    PANOC-lite is a proximal-gradient linesearch method with a cheaper backtracking procedure and novel merit function that achieves global subsequential convergence and local superlinear convergence under standard assumptions.

  3. Robust Learning Meets Quasar-Convex Optimization: Inexact High-Order Proximal-Point Methods

    math.OC 2026-05 unverdicted novelty 5.0

    Robust learning problems are formulated as quasar-convex optimization, and HiPPA is proposed as an inexact high-order proximal method with global and superlinear convergence guarantees.