English
Related papers

Related papers: Infinite-Width Limit of a Single Attention Layer: …

200 papers

It has been experimentally observed in recent years that multi-layer artificial neural networks have a surprising ability to generalize, even when trained with far more parameters than observations. Is there a theoretical basis for this?…

Machine Learning · Statistics 2018-09-19 Andrew R. Barron , Jason M. Klusowski

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

We study the implicit bias of gradient flow (i.e., gradient descent with infinitesimal step size) on linear neural network training. We propose a tensor formulation of neural networks that includes fully-connected, diagonal, and…

Machine Learning · Computer Science 2021-09-13 Chulhee Yun , Shankar Krishnan , Hossein Mobahi

While CNNs naturally lend themselves to densely sampled data, and sophisticated implementations are available, they lack the ability to efficiently process sparse data. In this work we introduce a suite of tools that exploit sparsity in…

Computer Vision and Pattern Recognition · Computer Science 2020-03-13 Timo Hackel , Mikhail Usvyatsov , Silvano Galliani , Jan D. Wegner , Konrad Schindler

In variational inference, the benefits of Bayesian models rely on accurately capturing the true posterior distribution. We propose using neural samplers that specify implicit distributions, which are well-suited for approximating complex…

Machine Learning · Computer Science 2023-11-10 Anshuk Uppal , Kristoffer Stensbo-Smidt , Wouter Boomsma , Jes Frellsen

To better understand the theoretical behavior of large neural networks, several works have analyzed the case where a network's width tends to infinity. In this regime, the effect of random initialization and the process of training a neural…

Machine Learning · Computer Science 2022-01-14 Florian Juengermann , Maxime Laasri , Marius Merkle

Attention networks have proven to be an effective approach for embedding categorical inference within a deep neural network. However, for many tasks we may want to model richer structural dependencies without abandoning end-to-end training.…

Computation and Language · Computer Science 2017-02-17 Yoon Kim , Carl Denton , Luong Hoang , Alexander M. Rush

Recent works have suggested that finite Bayesian neural networks may sometimes outperform their infinite cousins because finite networks can flexibly adapt their internal representations. However, our theoretical understanding of how the…

Machine Learning · Computer Science 2022-11-29 Jacob A. Zavatone-Veth , Abdulkadir Canatar , Benjamin S. Ruben , Cengiz Pehlevan

Understanding deep neural networks (DNNs) is a key challenge in the theory of machine learning, with potential applications to the many fields where DNNs have been successfully used. This article presents a scaling limit for a DNN being…

Statistics Theory · Mathematics 2019-06-04 Dyego Araújo , Roberto I. Oliveira , Daniel Yukimura

Recent progress has rapidly advanced our understanding of the mechanisms underlying in-context learning in modern attention-based neural networks. However, existing results focus exclusively on unimodal data; in contrast, the theoretical…

Machine Learning · Statistics 2026-05-19 Nicholas Barnfield , Subhabrata Sen , Pragya Sur

In this work, we address the question whether a sufficiently deep quantum neural network can approximate a target function as accurate as possible. We start with simple but typical physical situations that the target functions are physical…

Disordered Systems and Neural Networks · Physics 2021-09-01 Yadong Wu , Juan Yao , Pengfei Zhang , Hui Zhai

This work presents an analysis of the effectiveness of using standard shallow feed-forward networks to mimic the behavior of the attention mechanism in the original Transformer model, a state-of-the-art architecture for sequence-to-sequence…

Computation and Language · Computer Science 2024-02-06 Vukasin Bozic , Danilo Dordevic , Daniele Coppola , Joseph Thommes , Sidak Pal Singh

Deep neural networks have emerged as powerful tools for learning operators defined over infinite-dimensional function spaces. However, existing theories frequently encounter difficulties related to dimensionality and limited…

Machine Learning · Computer Science 2026-05-12 Jianfei Li , Shuo Huang , Han Feng , Ding-Xuan Zhou , Gitta Kutyniok

Given a cloud of $n$ data points in $\mathbb{R}^d$, consider all projections onto $m$-dimensional subspaces of $\mathbb{R}^d$ and, for each such projection, the empirical distribution of the projected points. What does this collection of…

Machine Learning · Statistics 2025-05-06 Andrea Montanari , Kangjie Zhou

Attention matrices are fundamental to transformer research, supporting a broad range of applications including interpretability, visualization, manipulation, and distillation. Yet, most existing analyses focus on individual attention heads…

Machine Learning · Computer Science 2026-01-27 Ido Andrew Atad , Itamar Zimerman , Shahar Katz , Lior Wolf

Primordial non-Gaussianity introduces a scale-dependent variation in the clustering of density peaks corresponding to rare objects. This variation, parametrized by the bias, is investigated on scales where a linear perturbation theory is…

Cosmology and Nongalactic Astrophysics · Physics 2011-04-22 Sirichai Chongchitnan , Joseph Silk

Neural networks have been very successful in many applications; we often, however, lack a theoretical understanding of what the neural networks are actually learning. This problem emerges when trying to generalise to new data sets. The…

Classical Analysis and ODEs · Mathematics 2022-11-22 Matthew Thorpe , Yves van Gennip

Obtaining theoretical guarantees for neural networks training appears to be a hard problem in a general case. Recent research has been focused on studying this problem in the limit of infinite width and two different theories have been…

Machine Learning · Statistics 2020-10-27 Eugene A. Golikov

Neural networks, a central tool in machine learning, have demonstrated remarkable, high fidelity performance on image recognition and classification tasks. These successes evince an ability to accurately represent high dimensional…

Machine Learning · Statistics 2023-02-08 Grant M. Rotskoff , Eric Vanden-Eijnden

We study the expressivity of one-dimensional (1D) ReLU deep neural networks through the lens of their linear regions. For randomly initialized, fully connected 1D ReLU networks (He scaling with nonzero bias) in the infinite-width limit, we…

Machine Learning · Computer Science 2025-12-10 Jonathan Kogan , Hayden Jananthan , Jeremy Kepner