paper-with-me

홈 › Papers

Accelerated Discovery of Machine-Learned Symmetries: Deriving the Exceptional Lie Groups G2, F4 and E6

2023-07-10 · Roy T. Forestano, Konstantin T. Matchev, Katia Matcheva, Alexander Roman, Eyup B. Unlu, Sarunas Verner

Recent work has applied supervised deep learning to derive continuous symmetry transformations that preserve the data labels and to obtain the corresponding algebras of symmetry generators. This letter introduces two improved algorithms that significantly speed up the discovery of these symmetry transformations. The new methods are demonstrated by deriving the complete set of generators for the unitary groups U(n) and the exceptional Lie groups $G_2$, $F_4$, and $E_6$. A third post-processing algorithm renders the found generators in sparse form. We benchmark the performance improvement of the new algorithms relative to the standard approach. Given the significant complexity of the exceptional Lie groups, our results demonstrate that this machine-learning method for discovering symmetries is completely general and can be applied to a wide variety of labeled datasets.

📄 PDF Abstract BibTeX arXiv:2307.04891

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Identifying the Group-Theoretic Structure of Machine-Learned Symmetries

2023-09-14 · Roy T. Forestano, Konstantin T. Matchev, Katia Matcheva, Alexander Roman 외

Deep learning was recently successfully used in deriving symmetry transformations that preserve important physics quantities. Being completely agnostic, these techniques postpone the identification of the discovered symm…

Deep Learning

Deep Learning Symmetries and Their Lie Groups, Algebras, and Subalgebras from First Principles

2023-01-13 · Roy T. Forestano, Konstantin T. Matchev, Katia Matcheva, Alexander Roman 외

We design a deep-learning algorithm for the discovery and identification of the continuous group of symmetries present in a labeled dataset. We use fully connected neural networks to model the symmetry transformations an…

Discovering Symmetry Groups with Flow Matching

2025-12-23 · Yuxuan Chen, Jung Yeon Park, Floor Eijkelboom, Jianke Yang 외 arxiv

Symmetry is fundamental to understanding physical systems and can improve performance and sample efficiency in machine learning. Both pursuits require knowledge of the underlying symmetries in data, yet discovering these…

Point Clouds

Spectral Discovery of Continuous Symmetries via Generalized Fourier Transforms

2026-03-07 · Pavan Karjol, Kumar Shubham, Prathosh AP arxiv

Continuous symmetries are fundamental to many scientific and learning problems, yet they are often unknown a priori. Existing symmetry discovery approaches typically search directly in the space of transformation generat…

Symmetry Detection

Symmetry-Informed Governing Equation Discovery

2024-05-27 · Jianke Yang, Wang Rao, Nima Dehmamy, Robin Walters 외

Despite the advancements in learning governing differential equations from observations of dynamical systems, data-driven methods are often unaware of fundamental physical laws, such as frame invariance. As a result, the…

Equation Discovery