Discriminative versus generative approaches to simulation-based inference

Machine Learning Science and Technology, vol. 6, pp. 030503

Abstract

Abstract Most of the fundamental, emergent, and phenomenological parameters of particle and nuclear physics are determined through parametric template fits. Simulations are used to populate histograms which are then matched to data. This approach is inherently lossy, since histograms are binned and low-dimensional. Deep learning has enabled unbinned and high-dimensional parameter estimation through neural likelihood(-ratio) estimation. We compare two approaches for neural simulation-based inference (NSBI): one based on discriminative learning (classification) and one based on generative modeling. These two approaches are directly evaluated on the same datasets, with a similar level of hyperparameter optimization in both cases. In addition to a Gaussian dataset, we study NSBI using a Higgs boson dataset from the FAIR Universe Challenge. We find that both the direct likelihood and likelihood ratio estimation are able to effectively extract parameters with reasonable uncertainties. For the numerical examples and within the set of hyperparameters studied, we found that the likelihood ratio method is more accurate and/or precise. Both methods have a significant spread from the network training and would require ensembling or other mitigation strategies in practice.

Authors 4

1. Benjamin Sluijter corresponding Aachen

   Leiden University · Lawrence Berkeley National Laboratory

   Affiliation as printed

   Leiden Institute of Physics, Universiteit Leiden, Leiden, RA 2300, The Netherlands

   Physics Division, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, United States of America

2. Sascha Diefenbacher corresponding

   Lawrence Berkeley National Laboratory

   Affiliation as printed

   Physics Division, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, United States of America

3. W. Bhimji corresponding

   Lawrence Berkeley National Laboratory · National Energy Research Scientific Computing Center

   Affiliation as printed

   National Energy Research Scientific Computing Center, Berkeley Lab, Berkeley, CA 94720, United States of America

4. Benjamin Philip Nachman corresponding

   Lawrence Berkeley National Laboratory · SLAC National Accelerator Laboratory · Stanford University

   Affiliation as printed

   Department of Particle Physics and Astrophysics, Stanford University, Stanford, CA 94305, United States of America

   Fundamental Physics Directorate, SLAC National Accelerator Laboratory, Menlo Park, CA 94025, United States of America

   Physics Division, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, United States of America