English
Related papers

Related papers: Equivariant Symmetry Breaking Sets

200 papers

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…

High Energy Physics - Experiment · Physics 2023-11-13 Edmund Witkowski , Daniel Whiteson

The combination of linear and nonlinear potentials, both shaped as a single well, enables competition between the confinement and expulsion induced by the former and latter potentials, respectively. We demonstrate that this setting leads to…

Pattern Formation and Solitons · Physics 2018-10-18 Dmitry A. Zezyulin , Mikhail E. Lebedev , Georgy L. Alfimov , Boris A. Malomed

Automatic tumor segmentation is a crucial step in medical image analysis for computer-aided diagnosis. Although the existing methods based on convolutional neural networks (CNNs) have achieved the state-of-the-art performance, many…

Image and Video Processing · Electrical Eng. & Systems 2020-05-11 Shuchao Pang , Anan Du , Mehmet A. Orgun , Yan Wang , Quanzheng Sheng , Shoujin Wang , Xiaoshui Huang , Zhemei Yu

Neural network parameterizations exhibit inherent symmetries that yield multiple equivalent minima within the loss landscape. Scale Graph Metanetworks (ScaleGMNs) explicitly leverage these symmetries by proposing an architecture equivariant…

Neural networks are emerging as a tool for scalable data-driven simulation of high-dimensional dynamical systems, especially in settings where numerical methods are infeasible or computationally expensive. Notably, it has been shown that…

Machine Learning · Computer Science 2024-09-16 Koen Minartz , Yoeri Poels , Simon Koop , Vlado Menkovski

We introduce the group-equivariant autoencoder (GE-autoencoder) -- a deep neural network (DNN) method that locates phase boundaries by determining which symmetries of the Hamiltonian have spontaneously broken at each temperature. We use…

Statistical Mechanics · Physics 2023-05-23 Devanshu Agrawal , Adrian Del Maestro , Steven Johnston , James Ostrowski

Equivariant neural networks provide a principled framework for incorporating symmetry into learning architectures and have been extensively analyzed through the lens of their separation power, that is, the ability to distinguish inputs…

Machine Learning · Computer Science 2026-02-04 Marco Pacini , Gabriele Santin , Bruno Lepri , Shubhendu Trivedi

Self-supervised learning for inverse problems allows to train a reconstruction network from noise and/or incomplete data alone. These methods have the potential of enabling learning-based solutions when obtaining ground-truth references for…

Computer Vision and Pattern Recognition · Computer Science 2026-05-14 Victor Sechaud , Jérémy Scanvic , Quentin Barthélemy , Patrice Abry , Julián Tachella

State-of-the-art deep learning systems often require large amounts of data and computation. For this reason, leveraging known or unknown structure of the data is paramount. Convolutional neural networks (CNNs) are successful examples of…

Computer Vision and Pattern Recognition · Computer Science 2020-12-07 Carlos Esteves

Spontaneous symmetry breaking (SSB) is responsible for structure formation in scenarios ranging from condensed matter to cosmology. SSB is broadly understood in terms of perturbations to the Hamiltonian governing the dynamics or to the…

Quantum Physics · Physics 2019-09-02 Luis Pedro García-Pintos , Diego Tielas , Adolfo del Campo

Graph is a highly generic and diverse representation, suitable for almost any data processing problem. Spectral graph theory has been shown to provide powerful algorithms, backed by solid linear algebra theory. It thus can be extremely…

Computer Vision and Pattern Recognition · Computer Science 2023-04-20 Or Streicher , Ido Cohen , Guy Gilboa

Spontaneous symmetry breaking (SSB) is a key concept in physics that for decades has played a crucial role in the description of many physical phenomena in a large number of different areas, like particle physics, cosmology, and…

Statistical Mechanics · Physics 2021-08-25 J. Smits , H. T. C. Stoof , P. van der Straten

Ensembles of quantum chaotic systems are expected to exhibit energy eigenvalues with random-matrix-like level repulsion between pairs of energies separated by less than the inverse Thouless time. Recent research has shown that exact and…

Statistical Mechanics · Physics 2022-04-06 Michael Winer , Brian Swingle

Group equivariance can overly constrain models if the symmetries in the group differ from those observed in data. While common methods address this by determining the appropriate level of symmetry at the dataset level, they are limited to…

Computer Vision and Pattern Recognition · Computer Science 2024-07-04 Alonso Urbano , David W. Romero

Steerable convolutional neural networks (SCNNs) enhance task performance by modelling geometric symmetries through equivariance constraints on weights. Yet, unknown or varying symmetries can lead to overconstrained weights and decreased…

Machine Learning · Computer Science 2025-05-09 Lars Veefkind , Gabriele Cesa

Learning policies for multi-entity systems in 3D environments is far more complicated against single-entity scenarios, due to the exponential expansion of the global state space as the number of entities increases. One potential solution of…

Machine Learning · Computer Science 2024-07-18 Runfa Chen , Ling Wang , Yu Du , Tianrui Xue , Fuchun Sun , Jianwei Zhang , Wenbing Huang

Spontaneous synchronization has long served as a paradigm for behavioral uniformity that can emerge from interactions in complex systems. When the interacting entities are identical and their coupling patterns are also identical, the…

Disordered Systems and Neural Networks · Physics 2016-12-30 Takashi Nishikawa , Adilson E. Motter

The concept of spontaneous symmetry breaking (SSB) generally lacks a simple and intuitive introduction in the literature. This gap is filled by defining SSB in a universal context beyond its usual applications in physics and by discussing…

Mathematical Physics · Physics 2020-10-26 Andreas Aste

Traditional supervised learning aims to learn an unknown mapping by fitting a function to a set of input-output pairs with a fixed dimension. The fitted function is then defined on inputs of the same dimension. However, in many settings,…

Machine Learning · Computer Science 2024-05-01 Eitan Levin , Mateo Díaz

In this work, we explore the trade-offs of explicit structural priors, particularly group equivariance. We address this through theoretical analysis and a comprehensive empirical study. To enable controlled and fair comparisons, we…

Computer Vision and Pattern Recognition · Computer Science 2025-06-03 Sharvaree Vadgama , Mohammad Mohaiminul Islam , Domas Buracas , Christian Shewmake , Artem Moskalev , Erik Bekkers