Pith. sign in

REVIEW 2 cited by

Curvature-Aware Derivative-Free 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 2109.13391 v2 pith:NQLKOVMC submitted 2021-09-27 math.OC cs.LG

classification math.OCcs.LG
keywords carsmethodssearchalphacars-crconvergescurvature-awarederivative-free
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
abstract

The paper discusses derivative-free optimization (DFO), which involves minimizing a function without access to gradients or directional derivatives, only function evaluations. Classical DFO methods, which mimic gradient-based methods, such as Nelder-Mead and direct search have limited scalability for high-dimensional problems. Zeroth-order methods have been gaining popularity due to the demands of large-scale machine learning applications, and the paper focuses on the selection of the step size $\alpha_k$ in these methods. The proposed approach, called Curvature-Aware Random Search (CARS), uses first- and second-order finite difference approximations to compute a candidate $\alpha_{+}$. We prove that for strongly convex objective functions, CARS converges linearly provided that the search direction is drawn from a distribution satisfying very mild conditions. We also present a Cubic Regularized variant of CARS, named CARS-CR, which converges in a rate of $\mathcal{O}(k^{-1})$ without the assumption of strong convexity. Numerical experiments show that CARS and CARS-CR match or exceed the state-of-the-arts on benchmark problem sets.

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. Fully Adaptive Zeroth-Order Method for Minimizing Functions with Compressible Gradients

    math.OC 2025-01 conditional novelty 6.0 of 10

    ZORO-FA is a fully adaptive zeroth-order method that provably finds eps-stationary points in O(s(log n)/eps^2) function evaluations when gradients are sufficiently compressible, and O(n^2/eps^2) otherwise.

  2. ZeroFlow: Overcoming Catastrophic Forgetting is Easier than You Think

    cs.CV 2025-01 conditional novelty 5.0 of 10

    ZeroFlow is a benchmark showing zeroth-order, forward-pass-only optimizers can match backpropagation-based continual learning on several datasets with about five times lower memory, plus three modest enhancements.

Pith tools