English
Related papers

Related papers: Neural Tangent Kernel Beyond the Infinite-Width Li…

200 papers

It is well understood that neural networks with carefully hand-picked weights provide powerful function approximation and that they can be successfully trained in over-parametrized regimes. Since over-parametrization ensures zero training…

Machine Learning · Computer Science 2024-05-21 G. Welper

Modern neural networks are often regarded as complex black-box functions whose behavior is difficult to understand owing to their nonlinear dependence on the data and the nonconvexity in their loss landscapes. In this work, we show that…

Machine Learning · Computer Science 2020-06-26 Wei Hu , Lechao Xiao , Ben Adlam , Jeffrey Pennington

In this article, we review the literature on statistical theories of neural networks from three perspectives: approximation, training dynamics and generative models. In the first part, results on excess risks for neural networks are…

Machine Learning · Statistics 2024-09-17 Namjoon Suh , Guang Cheng

Wide neural networks with linear output layer have been shown to be near-linear, and to have near-constant neural tangent kernel (NTK), in a region containing the optimization path of gradient descent. These findings seem counter-intuitive…

Machine Learning · Computer Science 2022-03-11 Chaoyue Liu , Libin Zhu , Mikhail Belkin

This paper presents two models of neural-networks and their training applicable to neural networks of arbitrary width, depth and topology, assuming only finite-energy neural activations; and a novel representor theory for neural networks in…

Machine Learning · Statistics 2024-05-27 Alistair Shilton , Sunil Gupta , Santu Rana , Svetha Venkatesh

Mathematical methods are developed to characterize the asymptotics of recurrent neural networks (RNN) as the number of hidden units, data samples in the sequence, hidden state updates, and training steps simultaneously grow to infinity. In…

Machine Learning · Computer Science 2026-01-15 Samuel Chun-Hei Lam , Justin Sirignano , Konstantinos Spiliopoulos

Data with low-dimensional nonlinear structure are ubiquitous in engineering and scientific problems. We study a model problem with such structure -- a binary classification task that uses a deep fully-connected neural network to classify…

Machine Learning · Statistics 2021-11-01 Tingran Wang , Sam Buchanan , Dar Gilboa , John Wright

For small training set sizes $P$, the generalization error of wide neural networks is well-approximated by the error of an infinite width neural network (NN), either in the kernel or mean-field/feature-learning regime. However, after a…

Machine Learning · Statistics 2022-12-26 Alexander Atanasov , Blake Bordelon , Sabarish Sainathan , Cengiz Pehlevan

We are interested in estimating the uncertainties of deep neural networks, which play an important role in many scientific and engineering problems. In this paper, we present a striking new finding that an ensemble of neural networks with…

Machine Learning · Computer Science 2022-12-05 Jayaraman J. Thiagarajan , Rushil Anirudh , Vivek Narayanaswamy , Peer-Timo Bremer

In multi-objective optimization, multiple loss terms are weighted and added together to form a single objective. These weights are chosen to properly balance the competing losses according to some meta-goal. For example, in physics-informed…

Numerical Analysis · Mathematics 2025-11-20 Max Hirsch , Federico Pichi

We study the average robustness notion in deep neural networks in (selected) wide and narrow, deep and shallow, as well as lazy and non-lazy training settings. We prove that in the under-parameterized setting, width has a negative effect…

Machine Learning · Computer Science 2023-02-13 Zhenyu Zhu , Fanghui Liu , Grigorios G Chrysos , Volkan Cevher

Recently, there has been growing evidence that if the width and depth of a neural network are scaled toward the so-called rich feature learning limit (\mup and its depth extension), then some hyperparameters -- such as the learning rate --…

Machine Learning · Computer Science 2024-11-14 Lorenzo Noci , Alexandru Meterez , Thomas Hofmann , Antonio Orvieto

State-of-the-art neural networks require extreme computational power to train. It is therefore natural to wonder whether they are optimally trained. Here we apply a recent advancement in stochastic thermodynamics which allows bounding the…

Machine Learning · Statistics 2023-07-28 Inbar Seroussi , Alexander A. Alemi , Moritz Helias , Zohar Ringel

In this paper, we theoretically prove that the deep ReLU neural networks do not lie in spurious local minima in the loss landscape under the Neural Tangent Kernel (NTK) regime, that is, in the gradient descent training dynamics of the deep…

Machine Learning · Statistics 2022-05-20 Tohru Nitta

How neural network behaves during the training over different choices of hyperparameters is an important question in the study of neural networks. In this work, inspired by the phase diagram in statistical mechanics, we draw the phase…

Machine Learning · Computer Science 2020-10-14 Tao Luo , Zhi-Qin John Xu , Zheng Ma , Yaoyu Zhang

One of the central problems in the study of deep learning theory is to understand how the structure properties, such as depth, width and the number of nodes, affect the expressivity of deep neural networks. In this work, we show a new…

Machine Learning · Computer Science 2020-10-16 Kaifeng Bu , Yaobo Zhang , Qingxian Luo

State-of-the-art neural network training methods depend on the gradient of the network function. Therefore, they cannot be applied to networks whose activation functions do not have useful derivatives, such as binary and discrete-time…

Machine Learning · Statistics 2025-06-24 Luke Eilers , Raoul-Martin Memmesheimer , Sven Goedeke

Quantized neural networks have drawn a lot of attention as they reduce the space and computational complexity during the inference. Moreover, there has been folklore that quantization acts as an implicit regularizer and thus can improve the…

Machine Learning · Computer Science 2022-06-14 Kaiqi Zhang , Ming Yin , Yu-Xiang Wang

A biological neural network in the cortex forms a neural field. Neurons in the field have their own receptive fields, and connection weights between two neurons are random but highly correlated when they are in close proximity in receptive…

Machine Learning · Computer Science 2023-01-10 Kaito Watanabe , Kotaro Sakamoto , Ryo Karakida , Sho Sonoda , Shun-ichi Amari

Bounds on the smallest eigenvalue of the neural tangent kernel (NTK) are a key ingredient in the analysis of neural network optimization and memorization. However, existing results require distributional assumptions on the data and are…

Machine Learning · Statistics 2024-05-24 Kedar Karhadkar , Michael Murray , Guido Montúfar