English
Related papers

Related papers: A Functional Perspective on Learning Symmetric Fun…

200 papers

Recent years have witnessed a hot wave of deep neural networks in various domains; however, it is not yet well understood theoretically. A theoretical characterization of deep neural networks should point out their approximation ability and…

Machine Learning · Computer Science 2022-10-28 Gao Zhang , Jin-Hui Wu , Shao-Qun Zhang

Neural networks that process the parameters of other neural networks find applications in domains as diverse as classifying implicit neural representations, generating neural network weights, and predicting generalization errors. However,…

Incorporating permutation equivariance into neural networks has proven to be useful in ensuring that models respect symmetries that exist in data. Symmetric tensors, which naturally appear in statistics, machine learning, and graph theory,…

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

Recent work on the representation of functions on sets has considered the use of summation in a latent space to enforce permutation invariance. In particular, it has been conjectured that the dimension of this latent space may remain fixed…

Machine Learning · Computer Science 2019-10-08 Edward Wagstaff , Fabian B. Fuchs , Martin Engelcke , Ingmar Posner , Michael Osborne

Recognizing symmetries in data allows for significant boosts in neural network training, which is especially important where training data are limited. In many cases, however, the exact underlying symmetry is present only in an idealized…

High Energy Physics - Phenomenology · Physics 2025-04-07 Seth Nabat , Aishik Ghosh , Edmund Witkowski , Gregor Kasieczka , Daniel Whiteson

We propose a general deep architecture for learning functions on multiple permutation-invariant sets. We also show how to generalize this architecture to sets of elements of any dimension by dimension equivariance. We demonstrate that our…

Machine Learning · Computer Science 2022-07-01 Kira Selby , Ahmad Rashid , Ivan Kobyzev , Mehdi Rezagholizadeh , Pascal Poupart

In this work we propose a new neural network architecture that efficiently implements and learns general purpose set-equivariant functions. Such a function f maps a set of entities x = {x1, . . . , xn} from one domain to a set of same…

Machine Learning · Computer Science 2019-09-23 Roland Vollgraf

Deep predictive models of neuronal activity have recently enabled several new discoveries about the selectivity and invariance of neurons in the visual cortex. These models learn a shared set of nonlinear basis functions, which are linearly…

Neurons and Cognition · Quantitative Biology 2024-06-19 Polina Turishcheva , Max Burg , Fabian H. Sinz , Alexander Ecker

Due to the over-parameterization nature, neural networks are a powerful tool for nonlinear function approximation. In order to achieve good generalization on unseen data, a suitable inductive bias is of great importance for neural networks.…

Machine Learning · Computer Science 2021-11-17 Weiyang Liu , Rongmei Lin , Zhen Liu , Li Xiong , Bernhard Schölkopf , Adrian Weller

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

Neural networks are a central technique in machine learning. Recent years have seen a wave of interest in applying neural networks to physical systems for which the governing dynamics are known and expressed through differential equations.…

Computational Physics · Physics 2020-01-31 M. Mattheakis , P. Protopapas , D. Sondak , M. Di Giovanni , E. Kaxiras

For the past 30 years or so, machine learning has stimulated a great deal of research in the study of approximation capabilities (expressive power) of a multitude of processes, such as approximation by shallow or deep neural networks,…

Machine Learning · Computer Science 2025-01-07 Hrushikesh Mhaskar

Symmetries built into a neural network have appeared to be very beneficial for a wide range of tasks as it saves the data to learn them. We depart from the position that when symmetries are not built into a model a priori, it is…

Machine Learning · Computer Science 2023-02-01 Artem Moskalev , Anna Sepliarskaia , Ivan Sosnovik , Arnold Smeulders

This work suggests using sampling theory to analyze the function space represented by neural networks. First, it shows, under the assumption of a finite input domain, which is the common case in training neural networks, that the function…

Machine Learning · Computer Science 2022-02-28 Raja Giryes

Invariances to translations have imbued convolutional neural networks with powerful generalization properties. However, we often do not know a priori what invariances are present in the data, or to what extent a model should be invariant to…

Machine Learning · Computer Science 2020-12-02 Gregory Benton , Marc Finzi , Pavel Izmailov , Andrew Gordon Wilson

In this paper, we consider the problem of learning functions over sets, i.e., functions that are invariant to permutations of input set items. Recent approaches of pooling individual element embeddings can necessitate extremely large…

Machine Learning · Computer Science 2020-01-13 Chirag Pabbaraju , Prateek Jain

A major challenge in the use of neural networks both for modeling human cognitive function and for artificial intelligence is the design of systems with the capacity to efficiently learn functions that support radical generalization. At the…

Machine Learning · Computer Science 2025-07-17 Cutter Dawes , Simon Segert , Kamesh Krishnamurthy , Jonathan D. Cohen

We study the family of functions that are represented by a linear convolutional neural network (LCN). These functions form a semi-algebraic subset of the set of linear maps from input space to output space. In contrast, the families of…

Machine Learning · Computer Science 2022-06-09 Kathlén Kohn , Thomas Merkh , Guido Montúfar , Matthew Trager

We propose a neural parameterization of convex sets by learning sublinear (positively homogeneous and convex) functions. Our networks implicitly represent both the support and gauge functions of a convex body. We prove a universal…

Optimization and Control · Mathematics 2026-05-06 Eloi Martinet

Deep learning has exhibited remarkable results across diverse areas. To understand its success, substantial research has been directed towards its theoretical foundations. Nevertheless, the majority of these studies examine how well deep…

Machine Learning · Statistics 2024-06-11 Hao Liu , Jiahui Cheng , Wenjing Liao