English
Related papers

Related papers: Infinite attention: NNGP and NTK for deep attentio…

200 papers

In modern theoretical analyses of neural networks, the infinite-width limit is often invoked to justify Gaussian approximations of neuron preactivations (e.g., via neural network Gaussian processes or Tensor Programs). However, these…

Machine Learning · Computer Science 2026-01-05 Mana Sakai , Ryo Karakida , Masaaki Imaizumi

There has recently been much work on the "wide limit" of neural networks, where Bayesian neural networks (BNNs) are shown to converge to a Gaussian process (GP) as all hidden layers are sent to infinite width. However, these results do not…

Machine Learning · Statistics 2020-07-07 Devanshu Agrawal , Theodore Papamarkou , Jacob Hinkle

Graph convolutional neural networks~(GCNs) have recently demonstrated promising results on graph-based semi-supervised classification, but little work has been done to explore their theoretical properties. Recently, several deep neural…

Machine Learning · Computer Science 2020-02-28 Jilin Hu , Jianbing Shen , Bin Yang , Ling Shao

Advanced deep neural networks (DNNs), designed by either human or AutoML algorithms, are growing increasingly complex. Diverse operations are connected by complicated connectivity patterns, e.g., various types of skip connections. Those…

Machine Learning · Computer Science 2022-10-13 Wuyang Chen , Wei Huang , Xinyu Gong , Boris Hanin , Zhangyang Wang

Graph neural networks (GNNs) are widely used as surrogates for costly experiments and first-principles simulations to study the behavior of compounds at atomistic scale, and their architectural complexity is constantly increasing to enable…

Machine Learning · Computer Science 2026-05-04 Arindam Chowdhury , Massimiliano Lupo Pasini

Expressiveness and generalization of deep models was recently addressed via the connection between neural networks (NNs) and kernel learning, where first-order dynamics of NN during a gradient-descent (GD) optimization were related to…

Machine Learning · Computer Science 2020-04-21 Dmitry Kopitkov , Vadim Indelman

We investigate how sparse neural activity affects the generalization performance of a deep Bayesian neural network at the large width limit. To this end, we derive a neural network Gaussian Process (NNGP) kernel with rectified linear unit…

Machine Learning · Computer Science 2023-05-19 Chanwoo Chun , Daniel D. Lee

A variety of infinitely wide neural architectures (e.g., dense NNs, CNNs, and transformers) induce Gaussian process (GP) priors over their outputs. These relationships provide both an accurate characterization of the prior predictive…

This paper aims to discuss the impact of random initialization of neural networks in the neural tangent kernel (NTK) theory, which is ignored by most recent works in the NTK theory. It is well known that as the network's width tends to…

Machine Learning · Statistics 2024-10-10 Guhan Chen , Yicheng Li , Qian Lin

Neural tangent kernels (NTKs) have been proposed to study the behavior of trained neural networks from the perspective of Gaussian processes. An important result in this body of work is the theorem of equivalence between a trained neural…

Machine Learning · Statistics 2025-01-22 Haoran Liu , Anthony Tai , David J. Crandall , Chunfeng Huang

Gaussian processes (GPs) are an attractive class of machine learning models because of their simplicity and flexibility as building blocks of more complex Bayesian models. Meanwhile, graph neural networks (GNNs) emerged recently as a…

Machine Learning · Computer Science 2023-02-14 Zehao Niu , Mihai Anitescu , Jie Chen

Recent works have revealed that infinitely-wide feed-forward or recurrent neural networks of any architecture correspond to Gaussian processes referred to as Neural Network Gaussian Processes (NNGPs). While these works have extended the…

Machine Learning · Statistics 2022-03-08 Hyungi Lee , Eunggu Yun , Hongseok Yang , Juho Lee

Attention-based architectures have become ubiquitous in machine learning, yet our understanding of the reasons for their effectiveness remains limited. This work proposes a new way to understand self-attention networks: we show that their…

Machine Learning · Computer Science 2023-08-02 Yihe Dong , Jean-Baptiste Cordonnier , Andreas Loukas

We aim to better understand attention over nodes in graph neural networks (GNNs) and identify factors influencing its effectiveness. We particularly focus on the ability of attention GNNs to generalize to larger, more complex or noisy…

Machine Learning · Computer Science 2019-10-29 Boris Knyazev , Graham W. Taylor , Mohamed R. Amer

Infinitely wide or deep neural networks (NNs) with independent and identically distributed (i.i.d.) parameters have been shown to be equivalent to Gaussian processes. Because of the favorable properties of Gaussian processes, this…

Machine Learning · Computer Science 2026-03-24 Steven Adams , Andrea Patanè , Morteza Lahijanian , Luca Laurenti

In recent years, the neural tangent kernel (NTK) and neural network Gaussian process kernel (NNGP) have given theoreticians tractable limiting cases of fully connected neural networks. However, the property of these kernels are poorly…

Machine Learning · Statistics 2026-04-28 David Holzmüller , Max Schölpple

While deep learning has achieved remarkable success across a wide range of applications, its theoretical understanding of representation learning remains limited. Deep neural kernels provide a principled framework to interpret…

Machine Learning · Computer Science 2025-11-11 Yong-Ming Tian , Shuang Liang , Shao-Qun Zhang , Feng-Lei Fan

Neural tangent kernels (NTKs) are a powerful tool for analyzing deep, non-linear neural networks. In the infinite-width limit, NTKs can easily be computed for most common architectures, yielding full analytic control over the training…

Machine Learning · Computer Science 2026-02-16 Max Guillen , Philipp Misof , Jan E. Gerken

Graph neural networks (GNNs) achieve remarkable performance in graph machine learning tasks but can be hard to train on large-graph data, where their learning dynamics are not well understood. We investigate the training dynamics of…

Machine Learning · Computer Science 2023-06-02 Sanjukta Krishnagopal , Luana Ruiz

Gaussian Processes (GPs) provide a convenient framework for specifying function-space priors, making them a natural choice for modeling uncertainty. In contrast, Bayesian Neural Networks (BNNs) offer greater scalability and extendability…

Machine Learning · Computer Science 2025-06-12 Marcin Sendera , Amin Sorkhei , Tomasz Kuśmierczyk