arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2203.06153cs.LGastro-ph.IMcs.AIhep-exhep-ph
收藏

物理学的对称群等变结构

Symmetry Group Equivariant Architectures for Physics

Flatiron Institute(熨斗研究所);ICEPP, University of Tokyo(东京大学ICEPP);Google Research(谷歌研究院);University of Chicago(芝加哥大学);Lawrence Berkeley National Laboratory(劳伦斯伯克利国家实验室);Massachusetts Institute of Technology(麻省理工学院);Yale University(耶鲁大学);Princeton University(普林斯顿大学)

Alexander Bogatskiy, Sanmay Ganguly, Thomas Kipf, Risi Kondor, David W. Miller, Daniel Murnane, Jan T. Offermann, Mariel Pettee, Phiala Shanahan, Chase Shimmin, Savannah Thais

摘要:

建立在数学对称性基础上的物理理论是我们理解宇宙广泛性质的重要组成部分。类似地,在机器学习领域,对对称性(如旋转或排列不变性)的认识推动了计算机视觉、自然语言处理和其他重要应用中令人印象深刻的性能突破。在这份报告中,我们认为,物理学界和更广泛的机器学习界都有很多需要理解的地方,并有可能从对对称群等变机器学习架构的研究中获得更深层次的投资。对于某些应用,在基础结构设计中引入对称性可以产生更经济的模型(即包含更少但更具表达性的学习参数),可解释的模型(即更可解释或直接映射到物理量)和/或可训练的模型(即在数据和计算要求方面更有效)。我们讨论了各种数字的优点评估这些模型以及一些潜在的好处和局限性,这些方法的各种物理应用。对这些方法的研究和投资将为未来的体系结构奠定基础,这些体系结构在新的计算范式下可能更加强大,并将提供对它们所应用的物理系统的更丰富的描述。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑