Pith. sign in

REVIEW

A Principle for Global Optimization with Gradients

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 2308.09556 v1 pith:B76CN5EI submitted 2023-08-18 math.OC cs.NAcs.NEmath.NAstat.ML

classification math.OCcs.NAcs.NEmath.NAstat.ML
keywords gradientsdirectionsglobalnon-localoptimizationprinciplesearchadaptation
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

This work demonstrates the utility of gradients for the global optimization of certain differentiable functions with many suboptimal local minima. To this end, a principle for generating search directions from non-local quadratic approximants based on gradients of the objective function is analyzed. Experiments measure the quality of non-local search directions as well as the performance of a proposed simplistic algorithm, of the covariance matrix adaptation evolution strategy (CMA-ES), and of a randomly reinitialized Broyden-Fletcher-Goldfarb-Shanno (BFGS) method.

Discussion (0). Continue with ORCID to comment.

Pith tools