A Stochastic Approach to the Subset Selection Problem via Mirror Descent

Dan Greenstein, Elazar Gershuni, Ilan Ben-Bassat, Yaroslav Fyodorov, Ran Moshe, Fiana Raiber, Alex Shtoff, Oren Somekh, Nadav Hallak

Keywords: Nonconvex Optimization, Subset Selection, Stochastic, Mirror Descent, Stochastic Mirror Descent

TL;DR: This paper proposes two stochastic formulations for the subset selection problem based on parametric distributions, derives unbiased stochastic gradient formulas, and establishes a rate result for the stochastic mirror descent in our setting.

Abstract:

The subset selection problem is fundamental in machine learning and other fields of computer science.
We introduce a stochastic formulation for the minimum cost subset selection problem in a black box setting, in which only the subset metric value is available.
Subsequently, we can handle two-stage schemes, with an outer subset-selection component and an inner subset cost evaluation component. We propose formulating the subset selection problem in a stochastic manner by choosing subsets at random from a distribution whose parameters are learned. Two stochastic formulations are proposed.
The first explicitly restricts the subset's cardinality, and the second yields the desired cardinality in expectation.
The distribution is parameterized by a decision variable, which we optimize using Stochastic Mirror Descent.
Our choice of distributions yields constructive closed-form unbiased stochastic gradient formulas and convergence guarantees, including a rate with favorable dependency on the problem parameters.
Empirical evaluation of selecting a subset of layers in transfer learning complements our theoretical findings and demonstrates the potential benefits of our approach.

Primary Area: optimization

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 6224