English
Related papers

Related papers: Scalars are universal: Equivariant machine learnin…

200 papers

We discuss a class of teleparallel scalar-torsion theories of gravity, which is parametrized by five free functions of the scalar field. The theories are formulated covariantly using a flat, but non-vanishing spin connection. We show how…

General Relativity and Quantum Cosmology · Physics 2018-09-12 Manuel Hohmann

Spin models are used in many studies of complex systems---be it condensed matter physics, neural networks, or economics---as they exhibit rich macroscopic behaviour despite their microscopic simplicity. Here we prove that all the physics of…

Statistical Mechanics · Physics 2016-06-15 Gemma De las Cuevas , Toby S. Cubitt

We study universal approximation of continuous functionals on compact subsets of products of Hilbert spaces. We prove that any such functional can be uniformly approximated by models that first take finitely many continuous linear…

Machine Learning · Computer Science 2026-02-04 Andrey Krylov , Maksim Penkin

Recent work has shown deep learning can accelerate the prediction of physical dynamics relative to numerical solvers. However, limited physical accuracy and an inability to generalize under distributional shift limit its applicability to…

Machine Learning · Computer Science 2021-03-17 Rui Wang , Robin Walters , Rose Yu

Many quantities we are interested in predicting are geometric tensors; we refer to this class of problems as geometric prediction. Attempts to perform geometric prediction in real-world scenarios have been limited to approximating them…

Machine Learning · Computer Science 2020-06-26 Raphael J. L. Townshend , Brent Townshend , Stephan Eismann , Ron O. Dror

Quantum neural network architectures that have little-to-no inductive biases are known to face trainability and generalization issues. Inspired by a similar problem, recent breakthroughs in machine learning address this challenge by…

Neural networks that are equivariant to rotations, translations, reflections, and permutations on n-dimensional geometric space have shown promise in physical modeling for tasks such as accurately but inexpensively modeling complex…

Machine Learning · Computer Science 2023-01-25 Yuanqing Wang , John D. Chodera

Covariant, self-interacting scalar quantum field theories admit solutions for low enough spacetime dimensions, but when additional divergences appear in higher dimensions, the traditional approach leads to results, such as triviality, that…

High Energy Physics - Theory · Physics 2015-05-27 John R. Klauder

We introduce deep scale-spaces (DSS), a generalization of convolutional neural networks, exploiting the scale symmetry structure of conventional image recognition tasks. Put plainly, the class of an image is invariant to the scale at which…

Machine Learning · Computer Science 2019-05-29 Daniel E. Worrall , Max Welling

Quantum neural networks (QNNs) are an analog of classical neural networks in the world of quantum computing, which are represented by a unitary matrix with trainable parameters. Inspired by the universal approximation property of classical…

Quantum Physics · Physics 2025-11-27 Ariel Neufeld , Philipp Schmocker , Viet Khoa Tran

Recent advances in deep learning and Transformers have driven major breakthroughs in robotics by employing techniques such as imitation learning, reinforcement learning, and LLM-based multimodal perception and decision-making. However,…

Group equivariant neural networks have proven effective in modelling a wide range of tasks where the data lives in a classical geometric space and exhibits well-defined group symmetries. However, these networks are not suitable for learning…

Machine Learning · Computer Science 2025-05-26 Edward Pearce-Crump

Incorporating symmetry as an inductive bias into neural network architecture has led to improvements in generalization, data efficiency, and physical consistency in dynamics modeling. Methods such as CNNs or equivariant neural networks use…

Machine Learning · Computer Science 2022-06-17 Rui Wang , Robin Walters , Rose Yu

Equivariant deep learning architectures exploit symmetries in learning problems to improve the sample efficiency of neural-network-based models and their ability to generalise. However, when modelling real-world data, learning problems are…

Machine Learning · Statistics 2024-11-12 Matthew Ashman , Cristiana Diaconu , Adrian Weller , Wessel Bruinsma , Richard E. Turner

Can we effectively learn a nonlinear representation in time comparable to linear learning? We describe a new algorithm that explicitly and adaptively expands higher-order interaction features over base linear representations. The algorithm…

Machine Learning · Computer Science 2014-10-03 Alekh Agarwal , Alina Beygelzimer , Daniel Hsu , John Langford , Matus Telgarsky

The effectiveness of Convolutional Neural Networks (CNNs) has been substantially attributed to their built-in property of translation equivariance. However, CNNs do not have embedded mechanisms to handle other types of transformations. In…

Computer Vision and Pattern Recognition · Computer Science 2020-02-07 Ivan Sosnovik , Michał Szmaja , Arnold Smeulders

We consider a generalized teleparallel theory of gravitation, where the action contains an arbitrary function of the torsion scalar and a scalar field, $f(T,\phi)$, thus encompassing the cases of $f(T)$ gravity and nonminimally coupled…

General Relativity and Quantum Cosmology · Physics 2018-05-23 Manuel Hohmann , Laur Järv , Ulbossyn Ualikhanova

Employing equivariance in neural networks leads to greater parameter efficiency and improved generalization performance through the encoding of domain knowledge in the architecture; however, the majority of existing approaches require an a…

Machine Learning · Computer Science 2023-05-31 Emmanouil Theodosis , Karim Helwani , Demba Ba

Any representation of data involves arbitrary investigator choices. Because those choices are external to the data-generating process, each choice leads to an exact symmetry, corresponding to the group of transformations that takes one…

Machine Learning · Statistics 2023-06-29 Soledad Villar , David W. Hogg , Weichi Yao , George A. Kevrekidis , Bernhard Schölkopf

We construct a generalization of the theory of symmetric functions involving functions of commuting and anticommuting (Grassmannian) variables. These new functions, called symmetric functions in superspace, are invariant under the diagonal…

Combinatorics · Mathematics 2007-05-23 P. Desrosiers , L. Lapointe , P. Mathieu