Pith. sign in

REVIEW 1 cited by

Exploiting Higher Order Smoothness in Derivative-free Optimization and Continuous Bandits

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 2006.07862 v4 pith:DUOH24XM submitted 2020-06-14 cs.LG math.OCstat.ML

classification cs.LGmath.OCstat.ML
keywords functionalgorithmoptimizationproblemboundsgradienthigherorder
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We study the problem of zero-order optimization of a strongly convex function. The goal is to find the minimizer of the function by a sequential exploration of its values, under measurement noise. We study the impact of higher order smoothness properties of the function on the optimization error and on the cumulative regret. To solve this problem we consider a randomized approximation of the projected gradient descent algorithm. The gradient is estimated by a randomized procedure involving two function evaluations and a smoothing kernel. We derive upper bounds for this algorithm both in the constrained and unconstrained settings and prove minimax lower bounds for any sequential search method. Our results imply that the zero-order algorithm is nearly optimal in terms of sample complexity and the problem parameters. Based on this algorithm, we also propose an estimator of the minimum value of the function achieving almost sharp oracle behavior. We compare our results with the state-of-the-art, highlighting a number of key improvements.

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. Optimal minimization of an unknown function in a nonparametric multivariate regression model thanks to a dimension reduction approach

    math.ST 2026-08 conditional novelty 6.0 of 10

    Combining local-polynomial Lasso variable selection with projected gradient descent yields near-minimax rates for estimating the minimizer and minimum of a sparse nonparametric regression function.

Pith tools