Symmetry Group Equivariant Architectures for Physics

Autor: Alexander Bogatskiy, Sanmay Ganguly, Thomas Kipf, Risi Kondor, Miller, David W., Daniel Murnane, Jan Tuzlić Offermann, Mariel Pettee, Phiala Shanahan, Chase Shimmin, Savannah Thais
Rok vydání: 2022
Předmět:
Zdroj: Jan Tuzlić Offermann
DOI: 10.48550/arxiv.2203.06153
Popis: 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. In this report, we argue that both the physics community and the broader machine learning community have much to understand and potentially to gain from a deeper investment in research concerning symmetry group equivariant machine learning architectures. For some 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). We discuss various figures of merit for evaluating these models as well as some potential benefits and limitations of these methods for a variety of physics applications. Research and investment into these approaches will lay the foundation for future architectures that are potentially more robust under new computational paradigms and will provide a richer description of the physical systems to which they are applied.
Comment: Contribution to Snowmass 2021
Databáze: OpenAIRE
Externí odkaz: