English
Related papers

Related papers: Universal Spin Models are Universal Approximators …

200 papers

A classical result in approximation theory states that for any continuous function \( \varphi: \mathbb{R} \to \mathbb{R} \), the set \( \operatorname{span}\{\varphi \circ g : g \in \operatorname{Aff}(\mathbb{R})\} \) is dense in \(…

Functional Analysis · Mathematics 2026-03-31 Eugene Bilokopytov , Foivos Xanthos

Neural networks are one of the most popularly used methods in machine learning and artificial intelligence nowadays. Due to the universal approximation theorem (Hornik et al. (1989)), a neural network with one hidden layer can approximate…

Statistics Theory · Mathematics 2019-09-18 Xiaoxi Shen , Chang Jiang , Lyudmila Sakhanenko , Qing Lu

Adversarial attacks against machine learning models are a rather hefty obstacle to our increasing reliance on these models. Due to this, provably robust (certified) machine learning models are a major topic of interest. Lipschitz continuous…

Machine Learning · Computer Science 2019-04-11 Jeremy E. J. Cohen , Todd Huster , Ra Cohen

This paper extends the proof of density of neural networks in the space of continuous (or even measurable) functions on Euclidean spaces to functions on compact sets of probability measures. By doing so the work parallels a more then a…

Machine Learning · Computer Science 2019-06-04 Tomas Pevny , Vojtech Kovarik

We explore unique considerations involved in fitting ML models to data with very high precision, as is often required for science applications. We empirically compare various function approximation methods and study how they scale with…

Machine Learning · Computer Science 2023-02-01 Eric J. Michaud , Ziming Liu , Max Tegmark

We study the approximation of shift-invariant or equivariant functions by deep fully convolutional networks from the dynamical systems perspective. We prove that deep residual fully convolutional networks and their continuous-layer…

Machine Learning · Computer Science 2023-05-19 Ting Lin , Zuowei Shen , Qianxiao Li

The problem of reconstructing functions from their asymptotic expansions in powers of a small variable is addressed by deriving a novel type of approximants. The derivation is based on the self-similar approximation theory, which presents…

Statistical Mechanics · Physics 2009-11-07 S. Gluzman , V. I. Yukalov , D. Sornette

Prediction, where observed data is used to quantify uncertainty about a future observation, is a fundamental problem in statistics. Prediction sets with coverage probability guarantees are a common solution, but these do not provide…

Statistics Theory · Mathematics 2022-11-22 Leonardo Cella , Ryan Martin

Model selection criteria are one of the most important tools in statistics. Proofs showing a model selection criterion is asymptotically optimal are tailored to the type of model (linear regression, quantile regression, penalized…

Statistics Theory · Mathematics 2025-10-17 Amaze Lusompa

Diffusion models are recent state-of-the-art methods for image generation and likelihood estimation. In this work, we generalize continuous-time diffusion models to arbitrary Riemannian manifolds and derive a variational framework for…

Machine Learning · Computer Science 2022-08-18 Chin-Wei Huang , Milad Aghajohari , Avishek Joey Bose , Prakash Panangaden , Aaron Courville

One of the basic principles of Approximation Theory is that the quality of approximations increase with the smoothness of the function to be approximated. Functions that are smooth in certain subdomains will have good approximations in…

Numerical Analysis · Mathematics 2016-12-23 Licia Lenarduzzi , Robert Schaback

Here several perfect simulation algorithms are brought under a single framework, and shown to derive from the same probabilistic result, called here the Fundamental Theorem of Perfect Simulation (FTPS). An exact simulation algorithm has…

Probability · Mathematics 2017-04-13 Mark Huber

In this note, we provide a unifying framework to investigate the computational complexity of classical spin models and give the full classification on spin models in terms of system dimensions, randomness, external magnetic fields and types…

Disordered Systems and Neural Networks · Physics 2019-11-12 Shi-Xin Zhang

We propose the GENERIC formalism informed neural networks (GFINNs) that obey the symmetric degeneracy conditions of the GENERIC formalism. GFINNs comprise two modules, each of which contains two components. We model each component using a…

Dynamical Systems · Mathematics 2022-07-13 Zhen Zhang , Yeonjong Shin , George Em Karniadakis

Unlike computation or the numerical analysis of differential equations, simulation does not have a well established conceptual and mathematical foundation. Simulation is an arguable unique union of modeling and computation. However,…

adap-org · Physics 2008-02-03 Steen Rasmussen , Christopher Barrett

We build on the dynamical systems approach to deep learning, where deep residual networks are idealized as continuous-time dynamical systems, from the approximation perspective. In particular, we establish general sufficient conditions for…

Machine Learning · Computer Science 2020-06-09 Qianxiao Li , Ting Lin , Zuowei Shen

The purpose of this paper is to investigate forcing as a tool to construct universal models. In particular, we look at theories of initial segments of the universe and show that any model of a sufficiently rich fragment of those theories…

Logic · Mathematics 2025-03-07 Francesco Parente , Matteo Viale

The models of spin systems defined on Euclidean space provide powerful machinery for studying a broad range of condensed matter phenomena. While the non-relativistic effective description is sufficient for most of the applications, it is…

High Energy Physics - Theory · Physics 2020-12-29 Danilo Artigas , Jakub Bilski , Sean Crowe , Jakub Mielczarek , Tomasz Trześniewski

The Universal Approximation Theorem posits that neural networks can theoretically possess unlimited approximation capacity with a suitable activation function and a freely chosen or trained set of parameters. However, a more practical…

Machine Learning · Computer Science 2024-09-26 Li Liu , Tengchao Yu , Heng Yong

Models can be simple for different reasons: because they yield a simple and computationally efficient interpretation of a generic dataset (e.g. in terms of pairwise dependences) - as in statistical learning - or because they capture the…

Disordered Systems and Neural Networks · Physics 2018-10-17 Alberto Beretta , Claudia Battistin , Clélia de Mulatier , Iacopo Mastromatteo , Matteo Marsili