English
Related papers

Related papers: Neural Network Layer Matrix Decomposition reveals …

200 papers

In this paper, we explain the universal approximation capabilities of deep residual neural networks through geometric nonlinear control. Inspired by recent work establishing links between residual networks and control systems, we provide a…

Machine Learning · Computer Science 2024-02-12 Paulo Tabuada , Bahman Gharesifard

The set of functions parameterized by a linear fully-connected neural network is a determinantal variety. We investigate the subvariety of functions that are equivariant or invariant under the action of a permutation group. Examples of such…

Machine Learning · Computer Science 2025-01-13 Kathlén Kohn , Anna-Laura Sattelberger , Vahid Shahverdi

This work studies approximation based on single-hidden-layer feedforward and recurrent neural networks with randomly generated internal weights. These methods, in which only the last layer of weights and a few hyperparameters are optimized,…

Probability · Mathematics 2021-02-17 Lukas Gonon , Lyudmila Grigoryeva , Juan-Pablo Ortega

We analyze the expressivity of a universal deep neural network that can be organized as a series of nested qubit rotations, accomplished by adjustable data re-uploads. While the maximal expressive power increases with the depth of the…

Quantum Physics · Physics 2023-11-13 Iván Panadero , Yue Ban , Hilario Espinós , Ricardo Puebla , Jorge Casanova , Erik Torrontegui

The fundamental learning theory behind neural networks remains largely open. What classes of functions can neural networks actually learn? Why doesn't the trained network overfit when it is overparameterized? In this work, we prove that…

Machine Learning · Computer Science 2020-06-02 Zeyuan Allen-Zhu , Yuanzhi Li , Yingyu Liang

A neural architecture with randomly initialized weights, in the infinite width limit, is equivalent to a Gaussian Random Field whose covariance function is the so-called Neural Network Gaussian Process kernel (NNGP). We prove that a…

Machine Learning · Computer Science 2024-04-29 Rustem Takhanov

Although neural networks traditionally are typically used to approximate functions defined over $\mathbb{R}^n$, the successes of graph neural networks, point-cloud neural networks, and manifold deep learning among other methods have…

Neural and Evolutionary Computing · Computer Science 2019-07-11 Stella Rose Biderman

It is well known that canonical recurrent neural networks (RNNs) face limitations in learning long-term dependencies which have been addressed by memory structures in long short-term memory (LSTM) networks. Neural Turing machines (NTMs) are…

Machine Learning · Computer Science 2023-10-06 Animesh Renanse , Alok Sharma , Rohitash Chandra

Linear layers in neural networks (NNs) trained by gradient descent can be expressed as a key-value memory system which stores all training datapoints and the initial weights, and produces outputs using unnormalised dot attention over the…

Machine Learning · Computer Science 2022-06-20 Kazuki Irie , Róbert Csordás , Jürgen Schmidhuber

We examine the necessary and sufficient complexity of neural networks to approximate functions from different smoothness spaces under the restriction of encodable network weights. Based on an entropy argument, we start by proving lower…

Functional Analysis · Mathematics 2020-09-21 Ingo Gühring , Mones Raslan

Deep learning employs multi-layer neural networks trained via the backpropagation algorithm. This approach has achieved success across many domains and relies on adaptive gradient methods such as the Adam optimizer. Sequence modeling…

Machine Learning · Computer Science 2025-07-16 Esmail Gumaan

Deep neural networks (DNNs) have demonstrated dominating performance in many fields; since AlexNet, networks used in practice are going wider and deeper. On the theoretical side, a long line of works has been focusing on training neural…

Machine Learning · Computer Science 2019-06-18 Zeyuan Allen-Zhu , Yuanzhi Li , Zhao Song

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

Neural network width and depth are fundamental aspects of network topology. Universal approximation theorems provide that with increasing width or depth, there exists a neural network that approximates a function arbitrarily well. These…

Machine Learning · Computer Science 2019-10-31 Ibrohim Nosirov , Jeffrey M. Hokanson

We explore the universality of neural encodings in convolutional neural networks trained on image classification tasks. We develop a procedure to directly compare the learned weights rather than their representations. It is based on a…

Machine Learning · Computer Science 2024-10-01 Florentin Guth , Brice Ménard

Building on the abstract Generalized Singular Value Decomposition (GSVD) theory of Brown et al. [2025], we prove that most modern neural architectures admit a generalized SVD representation in which they are left-invertible before a final…

Machine Learning · Computer Science 2026-05-11 Brian Charles Brown , Robert Bridges , David Grimsman , Mauricio Munoz , Sean Warnick

Interpretability has become an important issue in the machine learning field, along with the success of layered neural networks in various practical tasks. Since a trained layered neural network consists of a complex nonlinear relationship…

Machine Learning · Statistics 2018-05-22 Chihiro Watanabe , Kaoru Hiramatsu , Kunio Kashino

It is well-known that any matrix $A$ has an LU decomposition. Less well-known is the fact that it has a 'Toeplitz decomposition' $A = T_1 T_2 \cdots T_r$ where $T_i$'s are Toeplitz matrices. We will prove that any continuous function $f :…

Machine Learning · Computer Science 2022-11-28 Yucong Liu , Simiao Jiao , Lek-Heng Lim

The universal approximation theorem establishes that neural networks can approximate any continuous function on a compact set. Later works in approximation theory provide quantitative approximation rates for ReLU networks on the class of…

Machine Learning · Computer Science 2026-04-17 Jonathan W. Siegel , Snir Hordan , Hannah Lawrence , Ali Syed , Nadav Dym

This paper investigates the learning theory of Transformer networks for regression tasks on the compact Euclidean domain $[0,1]^d$ and $d$-dimensional compact Riemannian manifolds. We propose a novel constructive approximation framework for…

Machine Learning · Statistics 2026-05-12 Zhongjie Shi , Wenjing Liao