English

Reproducibility in Optimization: Theoretical Framework and Limits

Optimization and Control 2022-12-06 v4 Machine Learning Machine Learning

Abstract

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 optimization settings of interest such as smooth, non-smooth, and strongly-convex objective functions and establish tight bounds on the limits of reproducibility in each setting. Our analysis reveals a fundamental trade-off between computation and reproducibility: more computation is necessary (and sufficient) for better reproducibility.

Keywords

Cite

@article{arxiv.2202.04598,
  title  = {Reproducibility in Optimization: Theoretical Framework and Limits},
  author = {Kwangjun Ahn and Prateek Jain and Ziwei Ji and Satyen Kale and Praneeth Netrapalli and Gil I. Shamir},
  journal= {arXiv preprint arXiv:2202.04598},
  year   = {2022}
}

Comments

45 Pages; Accepted to NeurIPS 2022