English
Related papers

Related papers: Just One Layer Norm Guarantees Stable Extrapolatio…

200 papers

A primary advantage of neural networks lies in their feature learning characteristics, which is challenging to theoretically analyze due to the complexity of their training dynamics. We propose a new paradigm for studying feature learning…

Machine Learning · Computer Science 2024-12-30 Haobo Zhang , Jianfa Lai , Yicheng Li , Qian Lin , Jun S. Liu

In the era of large language models (LLMs), fine-tuning pretrained models has become ubiquitous. Yet the theoretical underpinning remains an open question. A central question is why only a few epochs of fine-tuning are typically sufficient…

Machine Learning · Statistics 2026-02-17 Zexuan Sun , Garvesh Raskutti

How well does a classic deep net architecture like AlexNet or VGG19 classify on a standard dataset such as CIFAR-10 when its width --- namely, number of channels in convolutional layers, and number of nodes in fully-connected internal…

Machine Learning · Computer Science 2019-11-05 Sanjeev Arora , Simon S. Du , Wei Hu , Zhiyuan Li , Ruslan Salakhutdinov , Ruosong Wang

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

This work bridges two important concepts: the Neural Tangent Kernel (NTK), which captures the evolution of deep neural networks (DNNs) during training, and the Neural Collapse (NC) phenomenon, which refers to the emergence of symmetry and…

Machine Learning · Computer Science 2023-11-07 Mariia Seleznova , Dana Weitzner , Raja Giryes , Gitta Kutyniok , Hung-Hsu Chou

The Neural Tangent Kernel (NTK) characterizes the behavior of infinitely-wide neural networks trained under least squares loss by gradient descent. Recent works also report that NTK regression can outperform finitely-wide neural networks…

Machine Learning · Computer Science 2021-12-09 Amir Zandieh , Insu Han , Haim Avron , Neta Shoham , Chaewon Kim , Jinwoo Shin

This paper demonstrates that in classification problems, fully connected neural networks (FCNs) and residual neural networks (ResNets) cannot be approximated by kernel logistic regression based on the Neural Tangent Kernel (NTK) under…

Machine Learning · Computer Science 2025-07-15 Zixiong Yu , Songtao Tian , Guhan Chen

We study how neural networks trained by gradient descent extrapolate, i.e., what they learn outside the support of the training distribution. Previous works report mixed empirical results when extrapolating with neural networks: while…

Machine Learning · Computer Science 2021-03-04 Keyulu Xu , Mozhi Zhang , Jingling Li , Simon S. Du , Ken-ichi Kawarabayashi , Stefanie Jegelka

Artificial neural networks have revolutionized machine learning in recent years, but a complete theoretical framework for their learning process is still lacking. Substantial advances were achieved for wide networks, within two disparate…

Machine Learning · Computer Science 2025-05-09 Yehonatan Avidan , Qianyi Li , Haim Sompolinsky

We consider optimizing two-layer neural networks in the mean-field regime where the learning dynamics of network weights can be approximated by the evolution in the space of probability measures over the weight parameters associated with…

Machine Learning · Computer Science 2022-10-19 Jingwei Zhang , Xunpeng Huang , Jincheng Yu

Given the complexity of genetic risk prediction, there is a critical need for the development of novel methodologies that can effectively capture intricate genotype--phenotype relationships (e.g., nonlinear) while remaining statistically…

Applications · Statistics 2025-10-03 Heng Ge , Qing Lu

The Neural Tangent Kernel (NTK) framework explains optimization in over-parameterized neural networks via approximately linearized dynamics, yielding exponential convergence guarantees. However, existing results are often overly pessimistic…

Machine Learning · Computer Science 2026-05-26 Ruchirinkil Marreddy , Chaoyue Liu

The Neural Tangent Kernel (NTK) characterizes the behavior of infinitely wide neural nets trained under least squares loss by gradient descent. However, despite its importance, the super-quadratic runtime of kernel methods limits the use of…

Machine Learning · Computer Science 2021-07-28 Amir Zandieh

In this paper we consider the limiting case of neural networks (NNs) architectures when the number of neurons in each hidden layer and the number of hidden layers tend to infinity thus forming a continuum, and we derive approximation errors…

Machine Learning · Computer Science 2026-05-12 Christophe Prieur , Mircea Lazar , Bogdan Robu

Neural networks trained on large datasets by minimizing a loss have become the state-of-the-art approach for resolving data science problems, particularly in computer vision, image processing and natural language processing. In spite of…

Computer Vision and Pattern Recognition · Computer Science 2022-11-08 Adrien Courtois , Jean-Michel Morel , Pablo Arias

While neural networks can be trained to map from one specific dataset to another, they usually do not learn a generalized transformation that can extrapolate accurately outside the space of training. For instance, a generative adversarial…

Quantitative Methods · Quantitative Biology 2019-01-25 Matthew Amodio , David van Dijk , Ruth Montgomery , Guy Wolf , Smita Krishnaswamy

Spectral bias is a significant phenomenon in neural network training and can be explained by neural tangent kernel (NTK) theory. In this work, we develop the NTK theory for deep neural networks with physics-informed loss, providing insights…

Machine Learning · Computer Science 2025-03-17 Weiye Gan , Yicheng Li , Qian Lin , Zuoqiang Shi

Convolutional Neural Networks (CNNs) are now a well-established tool for solving computational imaging problems. Modern CNN-based algorithms obtain state-of-the-art performance in diverse image restoration problems. Furthermore, it has been…

Computer Vision and Pattern Recognition · Computer Science 2024-10-22 Julián Tachella , Junqi Tang , Mike Davies

Past decades have witnessed a great interest in the distinction and connection between neural network learning and kernel learning. Recent advancements have made theoretical progress in connecting infinite-wide neural networks and Gaussian…

Machine Learning · Computer Science 2025-11-07 Shao-Qun Zhang , Zong-Yi Chen , Yong-Ming Tian , Xun Lu

In training a neural network with gradient descent (GD), each iteration induces a linear operator that governs first-order updates to a model's internal state variables. We define this operator as the Global Empirical Neural Tangent Kernel…

Machine Learning · Computer Science 2026-05-12 James Hazelden , Laura Driscoll , Eli Shlizerman , Eric Shea-Brown