English
Related papers

Related papers: SGD Learns Over-parameterized Networks that Provab…

200 papers

Adaptive gradient methods like AdaGrad are widely used in optimizing neural networks. Yet, existing convergence guarantees for adaptive gradient methods require either convexity or smoothness, and, in the smooth setting, only guarantee…

Machine Learning · Computer Science 2019-10-22 Xiaoxia Wu , Simon S. Du , Rachel Ward

We study nonparametric regression by an over-parameterized two-layer neural network trained by gradient descent (GD) in this paper. We show that, if the neural network is trained by GD with early stopping, then the trained network renders a…

Machine Learning · Statistics 2025-11-07 Yingzhen Yang , Ping Li

It is well-known that modern neural networks are vulnerable to adversarial examples. To mitigate this problem, a series of robust learning algorithms have been proposed. However, although the robust training error can be near zero via some…

Machine Learning · Computer Science 2022-10-17 Binghui Li , Jikai Jin , Han Zhong , John E. Hopcroft , Liwei Wang

This work is substituted by the paper in arXiv:2011.14066. Stochastic gradient descent is the de facto algorithm for training deep neural networks (DNNs). Despite its popularity, it still requires fine tuning in order to achieve its best…

Machine Learning · Statistics 2020-12-02 Vatsal Shah , Anastasios Kyrillidis , Sujay Sanghavi

Neural networks trained via gradient descent with random initialization and without any regularization enjoy good generalization performance in practice despite being highly overparametrized. A promising direction to explain this phenomenon…

Machine Learning · Computer Science 2022-05-17 Hancheng Min , Salma Tarmoun , Rene Vidal , Enrique Mallada

This dissertation studies a fundamental open challenge in deep learning theory: why do deep networks generalize well even while being overparameterized, unregularized and fitting the training data to zero error? In the first part of the…

Machine Learning · Computer Science 2021-10-19 Vaishnavh Nagarajan

Likelihood-based, or explicit, deep generative models use neural networks to construct flexible high-dimensional densities. This formulation directly contradicts the manifold hypothesis, which states that observed data lies on a…

Machine Learning · Statistics 2022-11-30 Gabriel Loaiza-Ganem , Brendan Leigh Ross , Jesse C. Cresswell , Anthony L. Caterini

Graph Convolutional Networks (GCN) is a pioneering model for graph-based semi-supervised learning. However, GCN does not perform well on sparsely-labeled graphs. Its two-layer version cannot effectively propagate the label information to…

Machine Learning · Computer Science 2025-02-24 Wei Ye , Zexi Huang , Yunqi Hong , Ambuj Singh

We discovered that the neural networks, especially the deep ReLU networks, demonstrate an `over-generalization' phenomenon. That is, the output values for the inputs that were not seen during training are mapped close to the output range…

Machine Learning · Computer Science 2024-10-23 Harsh Shrivastava

The generalization mystery in deep learning is the following: Why do over-parameterized neural networks trained with gradient descent (GD) generalize well on real datasets even though they are capable of fitting random datasets of…

Machine Learning · Computer Science 2022-06-07 Satrajit Chatterjee , Piotr Zielinski

We develop a convex analytic approach to analyze finite width two-layer ReLU networks. We first prove that an optimal solution to the regularized training problem can be characterized as extreme points of a convex set, where simple…

Machine Learning · Computer Science 2021-09-01 Tolga Ergen , Mert Pilanci

Despite the non-convex optimization landscape, over-parametrized shallow networks are able to achieve global convergence under gradient descent. The picture can be radically different for narrow networks, which tend to get stuck in…

Machine Learning · Statistics 2023-06-16 Rodrigo Veiga , Ludovic Stephan , Bruno Loureiro , Florent Krzakala , Lenka Zdeborová

Characterization of local minima draws much attention in theoretical studies of deep learning. In this study, we investigate the distribution of parameters in an over-parametrized finite neural network trained by ridge regularized empirical…

Machine Learning · Computer Science 2021-02-22 Sho Sonoda , Isao Ishikawa , Masahiro Ikeda

Recent works have shown that on sufficiently over-parametrized neural nets, gradient descent with relatively large initialization optimizes a prediction function in the RKHS of the Neural Tangent Kernel (NTK). This analysis leads to global…

Machine Learning · Statistics 2020-04-28 Colin Wei , Jason D. Lee , Qiang Liu , Tengyu Ma

We prove that two-layer (Leaky)ReLU networks initialized by e.g. the widely used method proposed by He et al. (2015) and trained using gradient descent on a least-squares loss are not universally consistent. Specifically, we describe a…

Machine Learning · Statistics 2022-06-10 David Holzmüller , Ingo Steinwart

It has been observed \citep{zhang2016understanding} that deep neural networks can memorize: they achieve 100\% accuracy on training data. Recent theoretical results explained such behavior in highly overparametrized regimes, where the…

Machine Learning · Computer Science 2019-09-27 Rong Ge , Runzhe Wang , Haoyu Zhao

The ability of deep neural networks to generalise well even when they interpolate their training data has been explained using various "simplicity biases". These theories postulate that neural networks avoid overfitting by first learning…

Machine Learning · Statistics 2023-05-29 Maria Refinetti , Alessandro Ingrosso , Sebastian Goldt

Deep neural networks generalize well despite being exceedingly overparameterized and being trained without explicit regularization. This curious phenomenon has inspired extensive research activity in establishing its statistical principles:…

Machine Learning · Statistics 2021-09-16 Ke Wang , Christos Thrampoulidis

Graph neural networks (GNNs), which learn the representation of a node by aggregating its neighbors, have become an effective computational tool in downstream applications. Over-smoothing is one of the key issues which limit the performance…

Machine Learning · Computer Science 2020-06-15 Kaixiong Zhou , Xiao Huang , Yuening Li , Daochen Zha , Rui Chen , Xia Hu

In spite of advances in understanding lazy training, recent work attributes the practical success of deep learning to the rich regime with complex inductive bias. In this paper, we study rich regime training empirically with benchmark…

Machine Learning · Computer Science 2021-03-01 Xinyan Li , Arindam Banerjee