English
Related papers

Related papers: Tensor Programs IIb: Architectural Universality of…

200 papers

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

Natural gradients have been widely studied from both theoretical and empirical perspectives, and it is commonly believed that natural gradients have advantages over standard (Euclidean) gradients in capturing the intrinsic geometric…

Machine Learning · Computer Science 2025-09-30 Qinxun Bai , Steven Rosenberg , Wei Xu

Recent theoretical work has established connections between over-parametrized neural networks and linearized models governed by he Neural Tangent Kernels (NTKs). NTK theory leads to concrete convergence and generalization results, yet the…

Machine Learning · Computer Science 2020-02-18 Yu Bai , Jason D. Lee

This paper studies the infinite-width limit of deep linear neural networks initialized with random parameters. We obtain that, when the number of neurons diverges, the training dynamics converge (in a precise sense) to the dynamics obtained…

Machine Learning · Computer Science 2022-12-01 Lénaïc Chizat , Maria Colombo , Xavier Fernández-Real , Alessio Figalli

By classifying infinite-width neural networks and identifying the *optimal* limit, Tensor Programs IV and V demonstrated a universal way, called $\mu$P, for *widthwise hyperparameter transfer*, i.e., predicting optimal hyperparameters of…

Neural and Evolutionary Computing · Computer Science 2023-10-13 Greg Yang , Dingli Yu , Chen Zhu , Soufiane Hayou

A theory of neural networks (NNs) built upon collective variables would provide scientists with the tools to better understand the learning process at every stage. In this work, we introduce two such variables, the entropy and the trace of…

Machine Learning · Computer Science 2023-05-03 Samuel Tovey , Sven Krippendorf , Konstantin Nikolaou , Christian Holm

Sequential training from task to task is becoming one of the major objects in deep learning applications such as continual learning and transfer learning. Nevertheless, it remains unclear under what conditions the trained model's…

Machine Learning · Statistics 2022-03-21 Ryo Karakida , Shotaro Akaho

Existing global convergence guarantees of (stochastic) gradient descent do not apply to practical deep networks in the practical regime of deep learning beyond the neural tangent kernel (NTK) regime. This paper proposes an algorithm, which…

Machine Learning · Computer Science 2021-04-19 Kenji Kawaguchi , Qingyun Sun

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

Variational quantum circuits are used in quantum machine learning and variational quantum simulation tasks. Designing good variational circuits or predicting how well they perform for given learning or optimization tasks is still unclear.…

Quantum Physics · Physics 2022-08-18 Junyu Liu , Francesco Tacchino , Jennifer R. Glick , Liang Jiang , Antonio Mezzacapo

A recent line of work has analyzed the theoretical properties of deep neural networks via the Neural Tangent Kernel (NTK). In particular, the smallest eigenvalue of the NTK has been related to the memorization capacity, the global…

Machine Learning · Statistics 2022-08-23 Quynh Nguyen , Marco Mondelli , Guido Montufar

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

Empirical neural tangent kernels (eNTKs) can provide a good understanding of a given network's representation: they are often far less expensive to compute and applicable more broadly than infinite width NTKs. For networks with O output…

Machine Learning · Statistics 2023-06-08 Mohamad Amin Mohamadi , Wonho Bae , Danica J. Sutherland

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

Many deep learning tasks have to deal with graphs (e.g., protein structures, social networks, source code abstract syntax trees). Due to the importance of these tasks, people turned to Graph Neural Networks (GNNs) as the de facto method for…

Machine Learning · Computer Science 2021-12-07 Shunhua Jiang , Yunze Man , Zhao Song , Zheng Yu , Danyang Zhuo

A common theoretical approach to understanding neural networks is to take an infinite-width limit, at which point the outputs become Gaussian process (GP) distributed. This is known as a neural network Gaussian process (NNGP). However, the…

Machine Learning · Statistics 2025-06-26 Ben Anson , Edward Milsom , Laurence Aitchison

We study the optimization of wide neural networks (NNs) via gradient flow (GF) in setups that allow feature learning while admitting non-asymptotic global convergence guarantees. First, for wide shallow NNs under the mean-field scaling and…

Machine Learning · Computer Science 2022-04-25 Zhengdao Chen , Eric Vanden-Eijnden , Joan Bruna

The generalization properties of Gaussian processes depend heavily on the choice of kernel, and this choice remains a dark art. We present the Neural Kernel Network (NKN), a flexible family of kernels represented by a neural network. The…

Machine Learning · Computer Science 2018-08-07 Shengyang Sun , Guodong Zhang , Chaoqi Wang , Wenyuan Zeng , Jiaman Li , Roger Grosse

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

The Neural Tangent Kernel (NTK) characterizes how a model's state evolves over Gradient Descent. Computing the full NTK matrix is often infeasible, especially for recurrent architectures. Here, we introduce a matrix-free perspective, using…

Machine Learning · Computer Science 2025-11-17 James Hazelden