English
Related papers

Related papers: On the Banach spaces associated with multi-layer R…

200 papers

We study the implicit regularization imposed by gradient descent for learning multi-layer homogeneous functions including feed-forward fully connected and convolutional deep neural networks with linear, ReLU or Leaky ReLU activation. We…

Machine Learning · Computer Science 2018-11-01 Simon S. Du , Wei Hu , Jason D. Lee

This paper develops a general theory for first-order descent methods whose search directions are restricted to a prescribed dictionary in a reflexive Banach space. Instead of assuming that the linear span of the dictionary is dense, as in…

Optimization and Control · Mathematics 2026-03-13 Miguel Berasategui , Pablo M. Berná , Antonio Falcó

How can local-search methods such as stochastic gradient descent (SGD) avoid bad local minima in training multi-layer neural networks? Why can they fit random labels even given non-convex and non-smooth architectures? Most existing theory…

Machine Learning · Computer Science 2019-05-28 Zeyuan Allen-Zhu , Yuanzhi Li , Zhao Song

A ridge is a function that is characterized by a one-dimensional profile (activation) and a multidimensional direction vector. Ridges appear in the theory of neural networks as functional descriptors of the effect of a neuron, with the…

Functional Analysis · Mathematics 2022-03-08 Michael Unser

In this work, we consider the approximation of a large class of bounded functions, with minimal regularity assumptions, by ReLU neural networks. We show that the approximation error can be bounded from above by a quantity proportional to…

Machine Learning · Statistics 2026-02-27 Owen Davis , Gianluca Geraci , Mohammad Motamed

It is an open problem whether an infinite-dimensional amenable Banach algebra exists whose underlying Banach space is reflexive. We give sufficient conditions for a reflexive, amenable Banach algebra to be finite-dimensional (and thus a…

Functional Analysis · Mathematics 2007-05-23 Volker Runde

While Bayesian neural networks (BNNs) hold the promise of being flexible, well-calibrated statistical models, inference often requires approximations whose consequences are poorly understood. We study the quality of common variational…

Machine Learning · Statistics 2020-10-26 Andrew Y. K. Foong , David R. Burt , Yingzhen Li , Richard E. Turner

In spite of finite dimension ReLU neural networks being a consistent factor behind recent deep learning successes, a theory of feature learning in these models remains elusive. Currently, insightful theories still rely on assumptions…

Machine Learning · Computer Science 2025-04-01 Devon Jarvis , Richard Klein , Benjamin Rosman , Andrew M. Saxe

In this paper, we develop a framework for showing that neural networks can overcome the curse of dimensionality in different high-dimensional approximation problems. Our approach is based on the notion of a catalog network, which is a…

Numerical Analysis · Mathematics 2021-10-13 Patrick Cheridito , Arnulf Jentzen , Florian Rossmannek

The purpose of this article is to develop a machinery to study the capacity of deep neural networks (DNNs) to approximate high-dimensional functions. In particular, we show that DNNs have the expressive power to overcome the curse of…

Numerical Analysis · Mathematics 2026-04-30 Pierfrancesco Beneventano , Patrick Cheridito , Robin Graeber , Arnulf Jentzen , Benno Kuckuck

We study the problem of approximating compactly-supported integrable functions while implementing their support set using feedforward neural networks. Our first main result transcribes this "structured" approximation problem into a…

Machine Learning · Computer Science 2022-08-02 Anastasis Kratsios , Behnoosh Zamanlooy

Universal approximation theory offers a foundational framework to verify neural network expressiveness, enabling principled utilization in real-world applications. However, most existing theoretical constructions are established by…

Machine Learning · Computer Science 2026-01-27 ZeYu Li , ShiJun Zhang , TieYong Zeng , FengLei Fan

In practice, multi-task learning (through learning features shared among tasks) is an essential property of deep neural networks (NNs). While infinite-width limits of NNs can provide good intuition for their generalization behavior, the…

Machine Learning · Computer Science 2022-10-21 Jakob Heiss , Josef Teichmann , Hanna Wutte

Let $X$ be a Banach holomorphic function space on the unit disk. A linear polynomial approximation scheme for $X$ is a sequence of bounded linear operators $T_n:X\to X$ with the property that, for each $f\in X$, the functions $T_n(f)$ are…

Functional Analysis · Mathematics 2020-11-09 Javad Mashreghi , Thomas Ransford

Recent studies show that a reproducing kernel Hilbert space (RKHS) is not a suitable space to model functions by neural networks as the curse of dimensionality (CoD) cannot be evaded when trying to approximate even a single ReLU neuron…

Machine Learning · Statistics 2024-06-27 Fanghui Liu , Leello Dadi , Volkan Cevher

The generalization mystery of overparametrized deep nets has motivated efforts to understand how gradient descent (GD) converges to low-loss solutions that generalize well. Real-life neural networks are initialized from small random values…

Machine Learning · Computer Science 2021-11-10 Kaifeng Lyu , Zhiyuan Li , Runzhe Wang , Sanjeev Arora

Targeting at sparse learning, we construct Banach spaces B of functions on an input space X with the properties that (1) B possesses an l1 norm in the sense that it is isometrically isomorphic to the Banach space of integrable functions on…

Machine Learning · Statistics 2015-01-16 Guohui Song , Haizhang Zhang , Fred J. Hickernell

This article concerns the expressive power of depth in deep feed-forward neural nets with ReLU activations. Specifically, we answer the following question: for a fixed $d_{in}\geq 1,$ what is the minimal width $w$ so that neural nets with…

Machine Learning · Statistics 2018-03-13 Boris Hanin , Mark Sellke

An approach to construct explicit integral representations for two-layer ReLU networks is presented, which provides relatively simple representations for any multivariate polynomial. Quantitative bounds are provided for a particular,…

Machine Learning · Statistics 2026-05-13 Anthony Lee

Path regularization has shown to be a very effective regularization to train neural networks, leading to a better generalization property than common regularizations i.e. weight decay, etc. We propose a first near-complete (as will be made…

Machine Learning · Computer Science 2026-04-09 Hao Yu