English
Related papers

Related papers: Early-stopped neural networks are consistent

200 papers

Despite a great deal of research, it is still unclear why neural networks are so susceptible to adversarial examples. In this work, we identify natural settings where depth-$2$ ReLU networks trained with gradient flow are provably…

Machine Learning · Computer Science 2022-10-05 Gal Vardi , Gilad Yehudai , Ohad Shamir

We study the generalization of two-layer ReLU neural networks in a univariate nonparametric regression problem with noisy labels. This is a problem where kernels (\emph{e.g.} NTK) are provably sub-optimal and benign overfitting does not…

Machine Learning · Computer Science 2024-06-12 Dan Qiao , Kaiqi Zhang , Esha Singh , Daniel Soudry , Yu-Xiang Wang

Early stopping is a widely used technique to prevent poor generalization performance when training an over-expressive model by means of gradient-based optimization. To find a good point to halt the optimizer, a common practice is to split…

Machine Learning · Computer Science 2017-06-07 Maren Mahsereci , Lukas Balles , Christoph Lassner , Philipp Hennig

We propose a metric for evaluating the generalization ability of deep neural networks trained with mini-batch gradient descent. Our metric, called gradient disparity, is the $\ell_2$ norm distance between the gradient vectors of two…

Machine Learning · Computer Science 2021-07-15 Mahsa Forouzesh , Patrick Thiran

With the motive of training all the parameters of a neural network, we study why and when one can achieve this by iteratively creating, training, and combining randomly selected subnetworks. Such scenarios have either implicitly or…

Machine Learning · Computer Science 2022-08-15 Fangshuo Liao , Anastasios Kyrillidis

Early stopping is a simple and widely used method to prevent over-training neural networks. We develop theoretical results to reveal the relationship between the optimal early stopping time and model dimension as well as sample size of the…

Machine Learning · Computer Science 2022-02-25 Ruoqi Shen , Liyao Gao , Yi-An Ma

We revisit the problem of learning a single neuron with ReLU activation under Gaussian input with square loss. We particularly focus on the over-parameterization setting where the student network has $n\ge 2$ neurons. We prove the global…

Machine Learning · Computer Science 2023-10-11 Weihang Xu , Simon S. Du

We analyze the implicit bias of constant step stochastic subgradient descent (SGD). We consider the setting of binary classification with homogeneous neural networks - a large class of deep neural networks with ReLU-type activation…

Machine Learning · Computer Science 2025-07-18 Sholom Schechtman , Nicolas Schreuder

We study the problem of learning one-hidden-layer neural networks with Rectified Linear Unit (ReLU) activation function, where the inputs are sampled from standard Gaussian distribution and the outputs are generated from a noisy teacher…

Machine Learning · Statistics 2018-06-21 Xiao Zhang , Yaodong Yu , Lingxiao Wang , Quanquan Gu

Modern machine learning models often employ a huge number of parameters and are typically optimized to have zero training loss; yet surprisingly, they possess near-optimal prediction performance, contradicting classical learning theory. We…

Machine Learning · Statistics 2021-06-08 Zhu Li , Zhi-Hua Zhou , Arthur Gretton

We investigate the generalization and optimization properties of shallow neural-network classifiers trained by gradient descent in the interpolating regime. Specifically, in a realizable scenario where model weights can achieve arbitrarily…

Machine Learning · Statistics 2023-03-29 Hossein Taheri , Christos Thrampoulidis

In this paper, we consider one dimensional (shallow) ReLU neural networks in which weights are chosen randomly and only the terminal layer is trained. First, we mathematically show that for such networks L2-regularized regression…

Machine Learning · Computer Science 2023-10-05 Jakob Heiss , Josef Teichmann , Hanna Wutte

Scaling limits, such as infinite-width limits, serve as promising theoretical tools to study large-scale models. However, it is widely believed that existing infinite-width theory does not faithfully explain the behavior of practical…

Machine Learning · Computer Science 2025-10-28 Moritz Haas , Sebastian Bordt , Ulrike von Luxburg , Leena Chennuru Vankadara

We present a novel algorithm for training deep neural networks in supervised (classification and regression) and unsupervised (reinforcement learning) scenarios. This algorithm combines the standard stochastic gradient descent and the…

Machine Learning · Computer Science 2023-05-23 Arunselvan Ramaswamy , Shalabh Bhatnagar , Naman Saxena

Deep neural networks (DNNs) trained with the logistic loss (i.e., the cross entropy loss) have made impressive advancements in various binary classification tasks. However, generalization analysis for binary classification with DNNs and…

Machine Learning · Statistics 2024-04-23 Zihan Zhang , Lei Shi , Ding-Xuan Zhou

Most of today's distributed machine learning systems assume {\em reliable networks}: whenever two machines exchange information (e.g., gradients or models), the network should guarantee the delivery of the message. At the same time, recent…

Distributed, Parallel, and Cluster Computing · Computer Science 2019-05-17 Chen Yu , Hanlin Tang , Cedric Renggli , Simon Kassing , Ankit Singla , Dan Alistarh , Ce Zhang , Ji Liu

Recent theoretical results show that gradient descent on deep neural networks under exponential loss functions locally maximizes classification margin, which is equivalent to minimizing the norm of the weight matrices under margin…

Machine Learning · Computer Science 2021-07-22 Andrzej Banburski , Fernanda De La Torre , Nishka Pant , Ishana Shastri , Tomaso Poggio

We consider the idealized setting of gradient flow on the population risk for infinitely wide two-layer ReLU neural networks (without bias), and study the effect of symmetries on the learned parameters and predictors. We first describe a…

Machine Learning · Computer Science 2023-02-10 Karl Hajjar , Lenaic Chizat

Over-parameterized models, such as large deep networks, often exhibit a double descent phenomenon, whereas a function of model size, error first decreases, increases, and decreases at last. This intriguing double descent behavior also…

Machine Learning · Computer Science 2020-09-22 Reinhard Heckel , Fatih Furkan Yilmaz

We explore the ability of overparameterized shallow ReLU neural networks to learn Lipschitz, nondifferentiable, bounded functions with additive noise when trained by Gradient Descent (GD). To avoid the problem that in the presence of noise,…

Machine Learning · Computer Science 2023-04-07 Ilja Kuzborskij , Csaba Szepesvári