Extracting Hyperparameter Constraints from Code - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2021

Extracting Hyperparameter Constraints from Code

Abstract

Machine-learning operators often have correctness constraints that cut across multiple hyperparameters and/or data. Violating these constraints causes runtime exceptions, but they are usually documented only informally or not at all. This paper presents a weakest precondition analysis for Python code. We demonstrate our analysis by extracting hyperparameter constraints for 45 sklearn operators. Our analysis is a step towards safer and more robust machine learning.
Fichier principal
Vignette du fichier
ssmls_iclr21.pdf (148.8 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03401683 , version 1 (25-10-2021)

Identifiers

  • HAL Id : hal-03401683 , version 1

Cite

Ingkarat Rak-Amnouykit, Ana Milanova, Guillaume Baudart, Martin Hirzel, Julian Dolby. Extracting Hyperparameter Constraints from Code. ICLR Workshop on Security and Safety in Machine Learning Systems, May 2021, Virtual, United States. ⟨hal-03401683⟩
80 View
261 Download

Share

Gmail Mastodon Facebook X LinkedIn More