Accounting for variance in machine learning benchmarks - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2021

Accounting for variance in machine learning benchmarks


Strong empirical evidence that one machine-learning algorithm A outperforms another one B ideally calls for multiple trials optimizing the learning pipeline over sources of variation such as data sampling, augmentation, parameter initialization, and hyperparameters choices. This is prohibitively expensive, and corners are cut to reach conclusions. We model the whole benchmarking process, revealing that variance due to data sampling, parameter initialization and hyperparameter choice impact markedly the results. We analyze the predominant comparison methods used today in the light of this variance. We show a counter-intuitive result that adding more sources of variation to an imperfect estimator approaches better the ideal estimator at a 51× reduction in compute cost. Building on these results, we study the error rate of detecting improvements, on five different deep-learning tasks/architectures. This study leads us to propose recommendations for performance comparisons.
Fichier principal
Vignette du fichier
main.pdf (870.74 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03177159 , version 1 (22-03-2021)


  • HAL Id : hal-03177159 , version 1


Xavier Bouthillier, Pierre Delaunay, Mirko Bronzi, Assya Trofimov, Brennan Nichyporuk, et al.. Accounting for variance in machine learning benchmarks. MLsys 2021 - 4th Conference on Machine Learning and Systems, Apr 2021, San Francisco (virtual), United States. ⟨hal-03177159⟩
252 View
254 Download


Gmail Mastodon Facebook X LinkedIn More