Skip to yearly menu bar Skip to main content


Reproducibility in Optimization: Theoretical Framework and Limits

Kwangjun Ahn · Prateek Jain · Ziwei Ji · Satyen Kale · Praneeth Netrapalli · Gil I Shamir

Hall J (level 1) #722

Keywords: [ First-Order Optimization ] [ Convex Optimization ] [ reproducibility ] [ inexact gradient oracles ]


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.

Chat is not available.