English
Related papers

Related papers: Limitations of the NTK for Understanding Generaliz…

200 papers

Modern deep learning models employ considerably more parameters than required to fit the training data. Whereas conventional statistical wisdom suggests such models should drastically overfit, in practice these models generalize remarkably…

Machine Learning · Statistics 2020-08-18 Ben Adlam , Jeffrey Pennington

Recent research shows that the dynamics of an infinitely wide neural network (NN) trained by gradient descent can be characterized by Neural Tangent Kernel (NTK) \citep{jacot2018neural}. Under the squared loss, the infinite-width NN trained…

Machine Learning · Statistics 2022-07-08 Yilan Chen , Wei Huang , Lam M. Nguyen , Tsui-Wei Weng

A major factor in the success of deep neural networks is the use of sophisticated architectures rather than the classical multilayer perceptron (MLP). Residual networks (ResNets) stand out among these powerful modern architectures. Previous…

Machine Learning · Computer Science 2021-05-25 Tom Tirer , Joan Bruna , Raja Giryes

We analyze the convergence of the averaged stochastic gradient descent for overparameterized two-layer neural networks for regression problems. It was recently found that a neural tangent kernel (NTK) plays an important role in showing the…

Machine Learning · Statistics 2021-06-14 Atsushi Nitanda , Taiji Suzuki

In this work, we investigate the generalization properties of random feature methods. Our analysis extends prior results for Tikhonov regularization to a broad class of spectral regularization techniques and further generalizes the setting…

Machine Learning · Statistics 2026-03-03 Mike Nguyen , Nicole Mücke

In this paper, we study the generalization performance of min $\ell_2$-norm overfitting solutions for the neural tangent kernel (NTK) model of a two-layer neural network with ReLU activation that has no bias term. We show that, depending on…

Machine Learning · Computer Science 2023-03-09 Peizhong Ju , Xiaojun Lin , Ness B. Shroff

Graph neural networks (GNNs) have achieved superior performance on node classification tasks in the last few years. Commonly, this is framed in a transductive semi-supervised learning setup wherein the entire graph, including the target…

Machine Learning · Computer Science 2021-10-11 Artun Bayer , Arindam Chowdhury , Santiago Segarra

The underlying mechanism of neural networks in capturing precise knowledge has been the subject of consistent research efforts. In this work, we propose a theoretical approach based on Neural Tangent Kernels (NTKs) to investigate such…

Computation and Language · Computer Science 2023-10-27 Xiaobing Sun , Jiaxi Li , Wei Lu

We perform a study on the generalization ability of the wide two-layer ReLU neural network on $\mathbb{R}$. We first establish some spectral properties of the neural tangent kernel (NTK): $a)$ $K_{d}$, the NTK defined on $\mathbb{R}^{d}$,…

Machine Learning · Statistics 2023-02-14 Jianfa Lai , Manyun Xu , Rui Chen , Qian Lin

Parameter-efficient fine-tuning for continual learning (PEFT-CL) has shown promise in adapting pre-trained models to sequential tasks while mitigating catastrophic forgetting problem. However, understanding the mechanisms that dictate…

Machine Learning · Computer Science 2026-02-27 Jingren Liu , Zhong Ji , YunLong Yu , Jiale Cao , Yanwei Pang , Jungong Han , Xuelong Li

Modern machine learning systems based on neural networks have shown great success in learning complex data patterns while being able to make good predictions on unseen data points. However, the limited interpretability of these systems…

Machine Learning · Computer Science 2020-07-22 Sarath Shekkizhar , Antonio Ortega

We introduce the neural tangent kernel (NTK) regime for two-layer neural operators and analyze their generalization properties. For early-stopped gradient descent (GD), we derive fast convergence rates that are known to be minimax optimal…

Machine Learning · Statistics 2024-12-24 Mike Nguyen , Nicole Mücke

Overparameterized fully-connected neural networks have been shown to behave like kernel models when trained with gradient descent, under mild conditions on the width, the learning rate, and the parameter initialization. In the limit of…

Machine Learning · Computer Science 2025-11-11 William St-Arnaud , Margarida Carvalho , Golnoosh Farnadi

Understanding the learning dynamics of neural networks is a central topic in the deep learning community. In this paper, we take an empirical perspective to study the learning dynamics of neural networks in real-world settings.…

Machine Learning · Computer Science 2025-04-15 Zhanpeng Zhou , Yongyi Yang , Jie Ren , Mahito Sugiyama , Junchi Yan

Large language models (LLMs) have achieved remarkable success across widespread tasks, yet their application in low-resource domains remains a significant challenge due to data scarcity and the high risk of overfitting. While in-domain data…

Computation and Language · Computer Science 2025-11-11 Pingjie Wang , Hongcheng Liu , Yusheng Liao , Ziqing Fan , Yaxin Du , Shuo Tang , Yanfeng Wang , Yu Wang

One of the chronic problems of deep-learning models is shortcut learning. In a case where the majority of training data are dominated by a certain feature, neural networks prefer to learn such a feature even if the feature is not…

Machine Learning · Computer Science 2026-02-04 Jinwoo Lim , Suhyun Kim , Soo-Mook Moon

Neural operators are aiming at approximating operators mapping between Banach spaces of functions, achieving much success in the field of scientific computing. Compared to certain deep learning-based solvers, such as Physics-Informed Neural…

Machine Learning · Computer Science 2025-01-13 Xianliang Xu , Ye Li , Zhongyi Huang

Neural models combining representation learning and reasoning in an end-to-end trainable manner are receiving increasing interest. However, their use is severely limited by their computational complexity, which renders them unusable on real…

Artificial Intelligence · Computer Science 2018-07-24 Pasquale Minervini , Matko Bosnjak , Tim Rocktäschel , Sebastian Riedel

Pruning neural networks before training has received increasing interest due to its potential to reduce training time and memory. One popular method is to prune the connections based on a certain metric, but it is not entirely clear what…

Machine Learning · Computer Science 2023-04-07 Yite Wang , Dawei Li , Ruoyu Sun

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