← Search

Gil I. Shamir

2 accepted papers

2022

Reproducibility in Optimization: Theoretical Framework and Limits

NeurIPS 2022accept

We initiate a formal study of reproducibility in optimization. We define a quantitative measure of reproducibility of optimization procedures in the face of noisy or error-prone operations such as inexact or stochastic gradient computations or inexact initialization. We then analyze several convex o…

Cited by 25SourcePDFScholar
2021

Finding Relevant Information via a Discrete Fourier Expansion

ICML 2021spotlight

A fundamental obstacle in learning information from data is the presence of nonlinear redundancies and dependencies in it. To address this, we propose a Fourier-based approach to extract relevant information in the supervised setting. We first develop a novel Fourier expansion for functions of corre…

Cited by 8SourcePDFScholar