Bulletin of the American Physical Society
APS April Meeting 2023
Volume 68, Number 6
Minneapolis, Minnesota (Apr 15-18)
Virtual (Apr 24-26); Time Zone: Central Time
Session D04: Equivariance Meets Covariance: Physics-informed Machine LearningInvited
|
Hide Abstracts |
Sponsoring Units: GDS Chair: Mariel Pettee, Lawrence Berkeley National Lab Room: MG Salon C - 3rd Floor |
Saturday, April 15, 2023 3:45PM - 4:21PM |
D04.00001: Equivariance Meets Covariance: Physics-informed Machine Learning Invited Speaker: Mariel Pettee Physical theories grounded in mathematical symmetries are an essential component of our understanding of a wide range of properties of the universe. Similarly, in the domain of machine learning, an awareness of symmetries such as rotation or permutation invariance has driven impressive performance breakthroughs in computer vision, natural language processing, and other important applications. For some ML applications, the introduction of symmetries into the fundamental structural design can yield models that are more economical (i.e. contain fewer, but more expressive, learned parameters), interpretable (i.e. more explainable or directly mappable to physical quantities), and/or trainable (i.e. more efficient in both data and computational requirements). Here, I'll provide an overview of some of the latest applications of equivariance & covariance in physics-informed ML. |
Saturday, April 15, 2023 4:21PM - 4:57PM |
D04.00002: Translation and Rotation Equivariant Normalizing Flow (TRENF) for Optimal Cosmological Analysis Invited Speaker: Biwei Dai In this talk we introduce Translation and Rotation Equivariant Normalizing Flow (TRENF), a generative Normalizing Flow (NF) model which explicitly incorporates translation and rotation symmetries. We apply TRENF to cosmological data analysis, where TRENF allows direct access to the high dimensional data likelihood p(x|y) as a function of the labels y, such as cosmological parameters. In contrast to traditional analyses based on summary statistics, the NF approach has no loss of information since it preserves the full dimensionality of the data. On Gaussian random fields, the TRENF likelihood agrees well with the analytical expression and saturates the Fisher information content in the labels y. On nonlinear cosmological overdensity fields from N-body simulations, TRENF leads to significant improvements in constraining power over the standard power spectrum summary statistic. |
Saturday, April 15, 2023 4:57PM - 5:33PM |
D04.00003: Equivariant Neural Networks for Particle Physics: PELICAN Invited Speaker: Alexander Bogatskiy We hold these truths to be self-evident: that all physics problems are created unequal, that they are endowed with their unique data structures and symmetries, that among these are tensor transformation laws, Lorentz symmetry, and permutation equivariance. A lot of attention has been paid to the applications of common machine learning methods in physics experiments and theory. However, much less attention is paid to the methods themselves and their viability as physics modeling tools. One of the most fundamental aspects of modeling physical phenomena is the identification of the symmetries that govern them. Incorporating symmetries into a model can reduce the risk of over-parameterization, and consequently improve a model's robustness and predictive power. Building off of previous work, I will demonstrate how careful choices in the details of network design – creating a model both simpler and more grounded in physics than the traditional approaches – can yield state-of-the-art performance despite the symmetry constraints. I will describe the Permutation-Equivariant and Lorentz-Invariant or Covariant Aggregator Network (PELICAN), which is based on a fusion of classical ideas from Invariant Theory and recent work on permutation-equivariant maps. As a proof of concept, it is applied to tagging and novel reconstruction (regression) problems. Particular attention will be paid to the remarkable explainability features of this kind of architecture, made possible only by the implementation of both permutation and full Lorentz symmetries. In particular, constituent-based regression with PELICAN results in particle-level features that can be visualized and interpreted in ways impossible with any traditional architecture. |
Follow Us |
Engage
Become an APS Member |
My APS
Renew Membership |
Information for |
About APSThe American Physical Society (APS) is a non-profit membership organization working to advance the knowledge of physics. |
© 2024 American Physical Society
| All rights reserved | Terms of Use
| Contact Us
Headquarters
1 Physics Ellipse, College Park, MD 20740-3844
(301) 209-3200
Editorial Office
100 Motor Pkwy, Suite 110, Hauppauge, NY 11788
(631) 591-4000
Office of Public Affairs
529 14th St NW, Suite 1050, Washington, D.C. 20045-2001
(202) 662-8700