Survey of machine-learning experimental methods at NeurIPS2019 and ICLR2020

Abstract : How do machine-learning researchers run their empirical validation? In the context of a push for improved reproducibility and benchmarking, this question is important to develop new tools for model comparison. This document summarizes a simple survey about experimental procedures, sent to authors of published papers at two leading conferences, NeurIPS 2019 and ICLR 2020. It gives a simple picture of how hyper-parameters are set, how many baselines and datasets are included, or how seeds are used.
Document type :
Reports
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-02447823
Contributor : Gaël Varoquaux <>
Submitted on : Tuesday, January 21, 2020 - 8:54:00 PM
Last modification on : Friday, January 24, 2020 - 1:29:46 AM

Files

ml_methods_survey.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02447823, version 1

Collections

Citation

Xavier Bouthillier, Gaël Varoquaux. Survey of machine-learning experimental methods at NeurIPS2019 and ICLR2020. [Research Report] Inria Saclay Ile de France. 2020. ⟨hal-02447823⟩

Share

Metrics

Record views

399

Files downloads

340