English
Related papers

Related papers: Floating-Point Neural Networks Are Provably Robust…

200 papers

Classical neural network approximation results take the form: for every function $f$ and every error tolerance $\epsilon > 0$, one constructs a neural network whose architecture and weights depend on $\epsilon$. This paper introduces a…

Neural and Evolutionary Computing · Computer Science 2025-11-20 Clemens Hutter , Valentin Abadie , Helmut Bölcskei

The quantum approximate optimization algorithm (QAOA) is a leading iterative variational quantum algorithm for heuristically solving combinatorial optimization problems. A large portion of the computational effort in QAOA is spent by the…

Quantum Physics · Physics 2022-08-23 Ohad Amosy , Tamuz Danzig , Ely Porat , Gal Chechik , Adi Makmal

The first decade of this century has seen the nascency of the first mathematical theory of general artificial intelligence. This theory of Universal Artificial Intelligence (UAI) has made significant contributions to many theoretical,…

Artificial Intelligence · Computer Science 2013-05-17 Marcus Hutter

Recently, versions of neural networks with infinite-dimensional affine operators inside the computational units (``neural operator'' networks) have been applied to learn solutions to differential equations. To enable practical computations,…

Functional Analysis · Mathematics 2026-02-03 Vinícius Luz Oliveira , Vladimir G. Pestov

We introduce so-called functional input neural networks defined on a possibly infinite dimensional weighted space with values also in a possibly infinite dimensional output space. To this end, we use an additive family to map the input…

Machine Learning · Statistics 2025-12-03 Christa Cuchiero , Philipp Schmocker , Josef Teichmann

We investigate the concept of Best Approximation for Feedforward Neural Networks (FNN) and explore their convergence properties through the lens of Random Projection (RPNNs). RPNNs have predetermined and fixed, once and for all, internal…

Machine Learning · Computer Science 2024-02-20 Gianluca Fabiani

In this work we consider a model problem of deep neural learning, namely the learning of a given function when it is assumed that we have access to its point values on a finite set of points. The deep neural network interpolant is the the…

Machine Learning · Statistics 2023-06-27 Michail Loulakis , Charalambos G. Makridakis

We review several of the most widely used techniques for training recurrent neural networks to approximate dynamical systems, then describe a novel algorithm for this task. The algorithm is based on an earlier theoretical result that…

Neural and Evolutionary Computing · Computer Science 2016-06-09 Adam Trischler , Gabriele MT D'Eleuterio

Infinitely wide or deep neural networks (NNs) with independent and identically distributed (i.i.d.) parameters have been shown to be equivalent to Gaussian processes. Because of the favorable properties of Gaussian processes, this…

Machine Learning · Computer Science 2026-03-24 Steven Adams , Andrea Patanè , Morteza Lahijanian , Luca Laurenti

The learning speed of feed-forward neural networks is notoriously slow and has presented a bottleneck in deep learning applications for several decades. For instance, gradient-based learning algorithms, which are used extensively to train…

Machine Learning · Statistics 2024-08-27 Deanna Needell , Aaron A. Nelson , Rayan Saab , Palina Salanevich , Olov Schavemaker

We present $\phi-$DeepONet, a physics-informed neural operator designed to learn mappings between function spaces that may contain discontinuities or exhibit non-smooth behavior. Classical neural operators are based on the universal…

Computational Engineering, Finance, and Science · Computer Science 2026-04-10 Sumanta Roy , Stephen T. Castonguay , Pratanu Roy , Michael D. Shields

We establish universal approximation theorems for infinite-dimensional geometric rough paths, i.e., we show that continuous functions on the space of infinite-dimensional weakly geometric H\"older continuous rough paths can be approximated…

Probability · Mathematics 2026-03-04 Sonja Cox , Asma Khedher , Thijs Maessen

The mean field algorithm is a widely used approximate inference algorithm for graphical models whose exact inference is intractable. In each iteration of mean field, the approximate marginals for each variable are updated by getting…

Machine Learning · Computer Science 2014-10-23 Yujia Li , Richard Zemel

Modern mobile neural networks with a reduced number of weights and parameters do a good job with image classification tasks, but even they may be too complex to be implemented in an FPGA for video processing tasks. The article proposes…

Computer Vision and Pattern Recognition · Computer Science 2020-12-04 Roman Solovyev , Alexander Kustov , Dmitry Telpukhov , Vladimir Rukhlov , Alexandr Kalinin

Function regression/approximation is a fundamental application of machine learning. Neural networks (NNs) can be easily trained for function regression using a sufficient number of neurons and epochs. The forward-forward learning algorithm…

Machine Learning · Computer Science 2025-10-16 Shivam Padmani , Akshay Joshi

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

Many approaches have been proposed to estimate camera poses by directly minimizing photometric error. However, due to the non-convex property of direct alignment, proper initialization is still required for these methods. Many robust norms…

Robotics · Computer Science 2019-10-17 Ke Wang , Kaixuan Wang , Shaojie Shen

This paper addresses the growing need to process non-Euclidean data, by introducing a geometric deep learning (GDL) framework for building universal feedforward-type models compatible with differentiable manifold geometries. We show that…

Machine Learning · Computer Science 2022-07-26 Anastasis Kratsios , Leonie Papon

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

Approximation Fixpoint Theory (AFT) is a powerful theory covering various semantics of non-monotonic reasoning formalisms in knowledge representation such as Logic Programming and Answer Set Programming. Many semantics of such non-monotonic…

Artificial Intelligence · Computer Science 2025-06-23 Linde Vanbesien , Bart Bogaerts , Marc Denecker