中文
相关论文

相关论文: Continuous Symmetry Discovery and Enforcement Usin…

200 篇论文

Symmetry plays a fundamental role in understanding natural phenomena and mathematical structures. This work develops a comprehensive theory for studying the persistent symmetries and degree of asymmetry of finite point configurations over…

代数拓扑 · 数学 2025-08-12 Jian Liu , Dong Chen , Guo-Wei Wei

We introduce group crosscoders, an extension of crosscoders that systematically discover and analyse symmetrical features in neural networks. While neural networks often develop equivariant representations without explicit architectural…

机器学习 · 计算机科学 2024-11-04 Liv Gorton

Despite the success of equivariant neural networks in scientific applications, they require knowing the symmetry group a priori. However, it may be difficult to know which symmetry to use as an inductive bias in practice. Enforcing the…

机器学习 · 计算机科学 2023-06-21 Jianke Yang , Robin Walters , Nima Dehmamy , Rose Yu

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, these algorithms may…

机器学习 · 计算机科学 2024-11-06 Jianke Yang , Wang Rao , Nima Dehmamy , Robin Walters , Rose Yu

We find the symmetry generators for the Friedman equations emanating from a perfect fluid source, in the presence of a cosmological constant term. The relevant dynamics is seen to be governed by two coupled, first order ordinary…

广义相对论与量子宇宙学 · 物理学 2020-09-23 T. Pailas , N. Dimakis , Andronikos Paliathanasis , Petros A. Terzis , T. Christodoulakis

We propose a simple method to identify a continuous Lie algebra symmetry in a dataset through regression by an artificial neural network. Our proposal takes advantage of the $ \mathcal{O}(\epsilon^2)$ scaling of the output variable under…

高能物理 - 唯象学 · 物理学 2022-06-01 Sean Craven , Djuna Croon , Daniel Cutting , Rachel Houtz

Symmetry is one of the most central concepts in physics, and it is no surprise that it has also been widely adopted as an inductive bias for machine-learning models applied to the physical sciences. This is especially true for models…

化学物理 · 物理学 2024-12-23 Marcel F. Langer , Sergey N. Pozdnyakov , Michele Ceriotti

The notion of a symmetric extension extends the usual notion of forcing by identifying a particular class of names which forms an intermediate model of ZF between the ground model and the generic extension, and often the axiom of choice…

逻辑 · 数学 2019-03-27 Asaf Karagila

Recognizing symmetries in data allows for significant boosts in neural network training. In many cases, however, the underlying symmetry is present only in an idealized dataset, and is broken in the training data, due to effects such as…

高能物理 - 实验 · 物理学 2023-11-13 Edmund Witkowski , Daniel Whiteson

Machine learning techniques are essential tools to compute efficient, yet accurate, force fields for atomistic simulations. This approach has recently been extended to incorporate quantum computational methods, making use of variational…

We propose a manifold matching approach to generative models which includes a distribution generator (or data generator) and a metric generator. In our framework, we view the real data set as some manifold embedded in a high-dimensional…

计算机视觉与模式识别 · 计算机科学 2021-08-30 Mengyu Dai , Haibin Hang

Symmetry is a key feature observed in nature (from flowers and leaves, to butterflies and birds) and in human-made objects (from paintings and sculptures, to manufactured objects and architectural design). Rotational, translational, and…

计算机视觉与模式识别 · 计算机科学 2019-08-28 Felice De Luca , Md Iqbal Hossain , Stephen Kobourov

We develop a unified categorical framework for gauging both continuous and finite symmetries in arbitrary spacetime dimensions. Our construction applies to geometric categories i.e. categories internal to stacks. This generalizes the…

数学物理 · 物理学 2026-01-26 Devon Stockall , Matthew Yu

Based on the convergence of their infinitesimal generators in the mixed topology, we provide a stability result for strongly continuous convex monotone semigroups on spaces of continuous functions. In contrast to previous results, we do not…

偏微分方程分析 · 数学 2026-05-19 Jonas Blessing , Michael Kupper , Max Nendel

Humans perceive and interact with hundreds of objects every day. In doing so, they need to employ mental models of these objects and often exploit symmetries in the object's shape and appearance in order to learn generalizable and…

计算机视觉与模式识别 · 计算机科学 2023-05-01 Stefano Ferraro , Toon Van de Maele , Tim Verbelen , Bart Dhoedt

Reflectional symmetry is ubiquitous in nature. While extrinsic reflectional symmetry can be easily parametrized and detected, intrinsic symmetry is much harder due to the high solution space. Previous works usually solve this problem by…

图形学 · 计算机科学 2019-11-04 Yi-Ling Qiao , Lin Gao , Shu-Zhi Liu , Ligang Liu , Yu-Kun Lai , Xilin Chen

In this paper we observe that information theoretical concepts are valuable tools for extracting information from images and, in particular, information on image symmetries. It is shown that the problem of detecting reflectional and…

计算机视觉与模式识别 · 计算机科学 2017-03-14 Agata Migalska , JP Lewis

Symmetry is a strong prior present in many object categories, yet standard benchmarks for 3D generative models rarely report whether this prior is preserved. We study symmetry preservation in unconditional point cloud generation. We first…

计算机视觉与模式识别 · 计算机科学 2026-05-19 Nicolas Caytuiro , Ivan Sipiran

Symmetry breaking for graphs and other combinatorial objects is notoriously hard. On the one hand, complete symmetry breaks are exponential in size. On the other hand, current, state-of-the-art, partial symmetry breaks are often considered…

计算机科学中的逻辑 · 计算机科学 2026-04-01 Michael Codish , Mikoláš Janota

We present a method for estimating the maximal symmetry of a continuous regression function. Knowledge of such a symmetry can be used to significantly improve modelling by removing the modes of variation resulting from the symmetries.…

统计方法学 · 统计学 2023-12-21 Louis G. Christie , John A. D. Aston