English
Related papers

Related papers: Width Provably Matters in Optimization for Deep Li…

200 papers

It has been experimentally observed in recent years that multi-layer artificial neural networks have a surprising ability to generalize, even when trained with far more parameters than observations. Is there a theoretical basis for this?…

Machine Learning · Statistics 2018-09-19 Andrew R. Barron , Jason M. Klusowski

We prove that the set of functions representable by ReLU neural networks with integer weights strictly increases with the network depth while allowing arbitrary width. More precisely, we show that $\lceil\log_2(n)\rceil$ hidden layers are…

Machine Learning · Computer Science 2023-02-27 Christian Haase , Christoph Hertrich , Georg Loho

How to develop slim and accurate deep neural networks has become crucial for real- world applications, especially for those employed in embedded systems. Though previous work along this research line has shown some promising results, most…

Neural and Evolutionary Computing · Computer Science 2019-10-02 Xin Dong , Shangyu Chen , Sinno Jialin Pan

We analyze the loss landscape and expressiveness of practical deep convolutional neural networks (CNNs) with shared weights and max pooling layers. We show that such CNNs produce linearly independent features at a "wide" layer which has…

Machine Learning · Computer Science 2018-06-07 Quynh Nguyen , Matthias Hein

There is some theoretical evidence that deep neural networks with multiple hidden layers have a potential for more efficient representation of multidimensional mappings than shallow networks with a single hidden layer. The question is…

Machine Learning · Computer Science 2019-10-08 Bernhard Bermeitinger , Tomas Hrycej , Siegfried Handschuh

Characterizing how neural network depth, width, and dataset size jointly impact model quality is a central problem in deep learning theory. We give here a complete solution in the special case of linear networks with output dimension one…

Machine Learning · Statistics 2023-05-16 Boris Hanin , Alexander Zlokapa

This article studies deep neural network expression rates for optimal stopping problems of discrete-time Markov processes on high-dimensional state spaces. A general framework is established in which the value function and continuation…

Probability · Mathematics 2022-10-20 Lukas Gonon

Deep neural networks have been used in various machine learning applications and achieved tremendous empirical successes. However, training deep neural networks is a challenging task. Many alternatives have been proposed in place of…

Machine Learning · Computer Science 2020-09-09 Yeonjong Shin

Deep neural networks are widely used prediction algorithms whose performance often improves as the number of weights increases, leading to over-parametrization. We consider a two-layered neural network whose first layer is frozen while the…

Machine Learning · Computer Science 2023-04-10 Roman Worschech , Bernd Rosenow

In deep learning, a central issue is to understand how neural networks efficiently learn high-dimensional features. To this end, we explore the gradient descent learning of a general Gaussian Multi-index model…

Machine Learning · Statistics 2026-02-06 Bohan Zhang , Zihao Wang , Hengyu Fu , Jason D. Lee

We give lower bounds on the amount of memory required by one-pass streaming algorithms for solving several natural learning problems. In a setting where examples lie in $\{0,1\}^d$ and the optimal classifier can be encoded using $\kappa$…

Machine Learning · Computer Science 2022-06-13 Gavin Brown , Mark Bun , Adam Smith

Does over-parameterization eliminate sub-optimal local minima for neural networks? An affirmative answer was given by a classical result in [59] for 1-hidden-layer wide neural networks. A few recent works have extended the setting to…

Machine Learning · Computer Science 2020-11-17 Tian Ding , Dawei Li , Ruoyu Sun

The expressive power of neural networks is important for understanding deep learning. Most existing works consider this problem from the view of the depth of a network. In this paper, we study how width affects the expressiveness of neural…

Machine Learning · Computer Science 2017-11-02 Zhou Lu , Hongming Pu , Feicheng Wang , Zhiqiang Hu , Liwei Wang

Despite the practical success of deep neural networks, a comprehensive theoretical framework that can predict practically relevant scores, such as the test accuracy, from knowledge of the training data is currently lacking. Huge…

Disordered Systems and Neural Networks · Physics 2024-06-27 R. Pacelli , S. Ariosto , M. Pastore , F. Ginelli , M. Gherardi , P. Rotondo

We develop a fast end-to-end method for training lightweight neural networks using multiple classifier heads. By allowing the model to determine the importance of each head and rewarding the choice of a single shallow classifier, we are…

Machine Learning · Computer Science 2020-04-20 Bartosz Wójcik , Maciej Wołczyk , Klaudia Bałazy , Jacek Tabor

The subject of deep learning has recently attracted users of machine learning from various disciplines, including: medical diagnosis and bioinformatics, financial market analysis and online advertisement, speech and handwriting recognition,…

Machine Learning · Computer Science 2018-03-12 Charles K. Chui , Shao-Bo Lin , Ding-Xuan Zhou

Modern deep neural networks (DNNs) represent a formidable challenge for theorists: according to the commonly accepted probabilistic framework that describes their performance, these architectures should overfit due to the huge number of…

Disordered Systems and Neural Networks · Physics 2022-03-03 S. Ariosto , R. Pacelli , F. Ginelli , M. Gherardi , P. Rotondo

A recurrent neural network (RNN) is a widely used deep-learning network for dealing with sequential data. Imitating a dynamical system, an infinite-width RNN can approximate any open dynamical system in a compact domain. In general, deep…

Machine Learning · Statistics 2023-03-30 Chang hoon Song , Geonho Hwang , Jun ho Lee , Myungjoo Kang

Many modern neural network architectures are trained in an overparameterized regime where the parameters of the model exceed the size of the training dataset. Sufficiently overparameterized neural network architectures in principle have the…

Machine Learning · Computer Science 2019-02-14 Samet Oymak , Mahdi Soltanolkotabi

Recent theoretical work has guaranteed that overparameterized networks trained by gradient descent achieve arbitrarily low training error, and sometimes even low test error. The required width, however, is always polynomial in at least one…

Machine Learning · Computer Science 2020-02-18 Ziwei Ji , Matus Telgarsky