English
Related papers

Related papers: Proportional infinite-width infinite-depth limit f…

200 papers

In this short note, we reify the connection between work on the storage capacity problem in wide two-layer treelike neural networks and the rapidly-growing body of literature on kernel limits of wide neural networks. Concretely, we observe…

Disordered Systems and Neural Networks · Physics 2022-05-02 Jacob A. Zavatone-Veth , Cengiz Pehlevan

We analyze the loss landscape and expressiveness of practical deep convolutional neural networks (CNNs) with shared weights and max pooling layers. We show that such CNNs produce linearly independent features at a "wide" layer which has…

Machine Learning · Computer Science 2018-06-07 Quynh Nguyen , Matthias Hein

We prove linear convergence of gradient descent to a global optimum for the training of deep residual networks with constant layer width and smooth activation function. We show that if the trained weights, as a function of the layer index,…

Machine Learning · Computer Science 2023-01-26 Rama Cont , Alain Rossier , RenYuan Xu

This book develops an effective theory approach to understanding deep neural networks of practical relevance. Beginning from a first-principles component-level picture of networks, we explain how to determine an accurate description of the…

Machine Learning · Computer Science 2022-05-31 Daniel A. Roberts , Sho Yaida , Boris Hanin

It is well-known that the distribution over functions induced through a zero-mean iid prior distribution over the parameters of a multi-layer perceptron (MLP) converges to a Gaussian process (GP), under mild conditions. We extend this…

Machine Learning · Computer Science 2019-12-02 Russell Tsuchida , Fred Roosta , Marcus Gallagher

In this work, we study the training and generalization performance of two-layer neural networks (NNs) after one gradient descent step under structured data modeled by Gaussian mixtures. While previous research has extensively analyzed this…

Machine Learning · Statistics 2025-05-20 Samet Demir , Zafer Dogan

Understanding the impact of data structure on the computational tractability of learning is a key challenge for the theory of neural networks. Many theoretical works do not explicitly model training data, or assume that inputs are drawn…

Machine Learning · Statistics 2022-05-23 Sebastian Goldt , Bruno Loureiro , Galen Reeves , Florent Krzakala , Marc Mézard , Lenka Zdeborová

Deep neural networks are highly expressive machine learning models with the ability to interpolate arbitrary datasets. Deep nets are typically optimized via first-order methods and the optimization process crucially depends on the…

Machine Learning · Statistics 2019-11-12 Talha Cihad Gulcu

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

Neural-net-induced Gaussian process (NNGP) regression inherits both the high expressivity of deep neural networks (deep NNs) as well as the uncertainty quantification property of Gaussian processes (GPs). We generalize the current NNGP to…

Machine Learning · Computer Science 2019-03-27 Guofei Pang , Liu Yang , George Em Karniadakis

The paper deals with the distribution of singular values of the input-output Jacobian of deep untrained neural networks in the limit of their infinite width. The Jacobian is the product of random matrices where the independent rectangular…

Machine Learning · Statistics 2022-07-13 Leonid Pastur

Classical neural networks with random initialization famously behave as Gaussian processes in the limit of many neurons, which allows one to completely characterize their training and generalization behavior. No such general understanding…

Quantum Physics · Physics 2025-02-07 Eric R. Anschuetz

It is well-known that the expressivity of a neural network depends on its architecture, with deeper networks expressing more complex functions. In the case of networks that compute piecewise linear functions, such as those with ReLU…

Machine Learning · Statistics 2019-06-12 Boris Hanin , David Rolnick

Parameter-space and function-space provide two different duality frames in which to study neural networks. We demonstrate that symmetries of network densities may be determined via dual computations of network correlation functions, even…

Machine Learning · Computer Science 2021-06-03 Anindita Maiti , Keegan Stoner , James Halverson

We study large deviations in the context of stochastic gradient descent for one-hidden-layer neural networks with quadratic loss. We derive a quenched large deviation principle, where we condition on an initial weight measure, and an…

Probability · Mathematics 2025-01-14 Christian Hirsch , Daniel Willhalm

The overparameterization of variational quantum circuits, as a model of Quantum Neural Networks (QNN), not only improves their trainability but also serves as a method for evaluating the property of a given ansatz by investigating their…

Quantum Physics · Physics 2023-05-23 Ali Rad

We propose a novel deep learning paradigm of differential flows that learn a stochastic differential equation transformations of inputs prior to a standard classification or regression function. The key property of differential Gaussian…

Machine Learning · Computer Science 2018-10-16 Pashupati Hegde , Markus Heinonen , Harri Lähdesmäki , Samuel Kaski

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

We theoretically characterize gradient descent dynamics in deep linear networks trained at large width from random initialization and on large quantities of random data. Our theory captures the ``wider is better" effect of…

Machine Learning · Computer Science 2025-06-17 Blake Bordelon , Cengiz Pehlevan

We study the asymptotic law of a network of interacting neurons when the number of neurons becomes infinite. Given a completely connected network of neurons in which the synaptic weights are Gaussian correlated random variables, we describe…

Probability · Mathematics 2013-12-16 Olivier Faugeras , James MacLaurin