English
Related papers

Related papers: Global Convergence of Deep Networks with One Wide …

200 papers

We consider the problem of training a deep orthogonal linear network, which consists of a product of orthogonal matrices, with no non-linearity in-between. We show that training the weights with Riemannian gradient descent is equivalent to…

Machine Learning · Statistics 2020-11-30 Pierre Ablin

We continue a long line of research aimed at proving convergence of depth 2 neural networks, trained via gradient descent, to a global minimum. Like in many previous works, our model has the following features: regression with quadratic…

Machine Learning · Computer Science 2022-12-06 Alexander Razborov

Training deep graph neural networks (GNNs) is notoriously hard. Besides the standard plights in training deep architectures such as vanishing gradients and overfitting, it also uniquely suffers from over-smoothing, information squashing,…

Machine Learning · Computer Science 2022-05-10 Tianlong Chen , Kaixiong Zhou , Keyu Duan , Wenqing Zheng , Peihao Wang , Xia Hu , Zhangyang Wang

Graph Convolutional Networks (GCNs) and their variants have received significant attention and achieved start-of-the-art performances on various recommendation tasks. However, many existing GCN models tend to perform recursive aggregations…

Information Retrieval · Computer Science 2020-06-09 Yue Xu , Hao Chen , Zengde Deng , Junxiong Zhu , Yanghua Li , Peng He , Wenyao Gao , Wenjun Xu

We study how permutation symmetries in overparameterized multi-layer neural networks generate `symmetry-induced' critical points. Assuming a network with $ L $ layers of minimal widths $ r_1^*, \ldots, r_{L-1}^* $ reaches a zero-loss…

Machine Learning · Computer Science 2021-09-14 Berfin Şimşek , François Ged , Arthur Jacot , Francesco Spadaro , Clément Hongler , Wulfram Gerstner , Johanni Brea

We study the approximation of the median of $d$ inputs using ReLU neural networks. We present depth-width tradeoffs under several settings, culminating in a constant-depth, linear-width construction that achieves exponentially small…

Machine Learning · Computer Science 2026-02-10 Abhigyan Dutta , Itay Safran , Paul Valiant

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

The paper contains approximation guarantees for neural networks that are trained with gradient flow, with error measured in the continuous $L_2(\mathbb{S}^{d-1})$-norm on the $d$-dimensional unit sphere and targets that are Sobolev smooth.…

Machine Learning · Computer Science 2023-09-12 G. Welper

Empirical studies show that gradient-based methods can learn deep neural networks (DNNs) with very good generalization performance in the over-parameterization regime, where DNNs can easily fit a random labeling of the training data. Very…

Machine Learning · Computer Science 2019-11-28 Yuan Cao , Quanquan Gu

We study regularized deep neural networks (DNNs) and introduce a convex analytic framework to characterize the structure of the hidden layers. We show that a set of optimal hidden layer weights for a norm regularized DNN training problem…

Machine Learning · Computer Science 2021-06-14 Tolga Ergen , Mert Pilanci

We develop a mathematically rigorous framework for multilayer neural networks in the mean field regime. As the network's widths increase, the network's learning trajectory is shown to be well captured by a meaningful and dynamically…

Machine Learning · Computer Science 2023-02-14 Phan-Minh Nguyen , Huy Tuan Pham

We study the complexity of training neural network models with one hidden nonlinear activation layer and an output weighted sum layer. We analyze Gradient Descent applied to learning a bounded target function on $n$ real-valued inputs. We…

Machine Learning · Computer Science 2019-05-28 Santosh Vempala , John Wilmes

Aimed at explaining the surprisingly good generalization behavior of overparameterized deep networks, recent works have developed a variety of generalization bounds for deep learning, all based on the fundamental learning-theoretic…

Machine Learning · Computer Science 2021-10-19 Vaishnavh Nagarajan , J. Zico Kolter

The parameter space for any fixed architecture of feedforward ReLU neural networks serves as a proxy during training for the associated class of functions - but how faithful is this representation? It is known that many different parameter…

Machine Learning · Computer Science 2023-06-13 J. Elisenda Grigsby , Kathryn Lindsey , David Rolnick

The universal approximation theorem states that a neural network with one hidden layer can approximate continuous functions on compact sets with any desired precision. This theorem supports using neural networks for various applications,…

Machine Learning · Computer Science 2024-08-13 Marcos Eduardo Valle , Wington L. Vital , Guilherme Vieira

We propose a new technique that boosts the convergence of training generative adversarial networks. Generally, the rate of training deep models reduces severely after multiple iterations. A key reason for this phenomenon is that a deep…

Machine Learning · Statistics 2018-06-15 Atsushi Nitanda , Taiji Suzuki

Neural networks often operate in the overparameterized regime, in which there are far more parameters than training samples, allowing the training data to be fit perfectly. That is, training the network effectively learns an interpolating…

Machine Learning · Computer Science 2025-03-19 Suzanna Parkinson , Greg Ongie , Rebecca Willett

We consider the dynamics of gradient descent (GD) in overparameterized single hidden layer neural networks with a squared loss function. Recently, it has been shown that, under some conditions, the parameter values obtained using GD achieve…

Machine Learning · Computer Science 2021-05-17 Siddhartha Satpathi , R Srikant

The first provably efficient algorithm for learning graph neural networks (GNNs) with one hidden layer for node information convolution is provided in this paper. Two types of GNNs are investigated, depending on whether labels are attached…

Machine Learning · Computer Science 2020-12-08 Qunwei Li , Shaofeng Zou , Wenliang Zhong

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