4.4 Article

Optimization and supervised machine learning methods for fitting numerical physics models without derivatives*

Journal

Publisher

IOP Publishing Ltd
DOI: 10.1088/1361-6471/abd009

Keywords

model calibration; numerical optimization; density functional theory; machine learning in physics

Funding

  1. US Department of Energy, Office of Science, Office of Advanced Scientific Computing Research [DE-AC02-06CH11357]
  2. US Department of Energy, Office of Science, Office of Nuclear Physics [DE-SC0013365, DE-SC0018083]
  3. NUCLEI SciDAC-4 collaboration

Ask authors/readers for more resources

This paper discusses the calibration of a computationally expensive nuclear physics model, focusing on the performance of optimization-based training algorithms when training data and concurrent model evaluations are limited. Using the Fayans energy density functional model as a case study, considerations for tuning in different computational settings are analyzed and illustrated.
We address the calibration of a computationally expensive nuclear physics model for which derivative information with respect to the fit parameters is not readily available. Of particular interest is the performance of optimization-based training algorithms when dozens, rather than millions or more, of training data are available and when the expense of the model places limitations on the number of concurrent model evaluations that can be performed. As a case study, we consider the Fayans energy density functional model, which has characteristics similar to many model fitting and calibration problems in nuclear physics. We analyze hyperparameter tuning considerations and variability associated with stochastic optimization algorithms and illustrate considerations for tuning in different computational settings.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.4
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available