English
Related papers

Related papers: Width and Depth Limits Commute in Residual Network…

200 papers

Information propagation characterizes how input correlations evolve across layers in deep neural networks. This framework has been well studied using mean-field theory, which assumes infinitely wide networks. However, these assumptions…

Machine Learning · Computer Science 2026-01-21 Giuseppe Alessio D'Inverno , Zhiyuan Hu , Leo Davy , Michael Unser , Gianluigi Rozza , Jonathan Dong

We show that the error of iteratively magnitude-pruned networks empirically follows a scaling law with interpretable coefficients that depend on the architecture and task. We functionally approximate the error of the pruned networks,…

Machine Learning · Computer Science 2021-07-06 Jonathan S. Rosenfeld , Jonathan Frankle , Michael Carbin , Nir Shavit

Deep neural networks' remarkable ability to correctly fit training data when optimized by gradient-based algorithms is yet to be fully understood. Recent theoretical results explain the convergence for ReLU networks that are wider than…

Machine Learning · Computer Science 2021-02-09 Asaf Noy , Yi Xu , Yonathan Aflalo , Lihi Zelnik-Manor , Rong Jin

Residual networks (ResNets) have displayed impressive results in pattern recognition and, recently, have garnered considerable theoretical interest due to a perceived link with neural ordinary differential equations (neural ODEs). This link…

Machine Learning · Computer Science 2021-06-11 Alain-Sam Cohen , Rama Cont , Alain Rossier , Renyuan Xu

Conventional scaling of neural networks typically involves designing a base network and growing different dimensions like width, depth, etc. of the same by some predefined scaling factors. We introduce an automated scaling approach…

Machine Learning · Computer Science 2024-02-21 Akash Guna R. T , Arnav Chavan , Deepak Gupta

Modern neural networks (NN) featuring a large number of layers (depth) and units per layer (width) have achieved a remarkable performance across many domains. While there exists a vast literature on the interplay between infinitely wide NNs…

Machine Learning · Statistics 2021-09-21 Stefano Peluchetti , Stefano Favaro

We prove limitations on what neural networks trained by noisy gradient descent (GD) can efficiently learn. Our results apply whenever GD training is equivariant, which holds for many standard architectures and initializations. As…

Machine Learning · Computer Science 2022-10-17 Emmanuel Abbe , Enric Boix-Adsera

This paper investigates the approximation power of three types of random neural networks: (a) infinite width networks, with weights following an arbitrary distribution; (b) finite width networks obtained by subsampling the preceding…

Machine Learning · Computer Science 2019-10-21 Bolton Bailey , Ziwei Ji , Matus Telgarsky , Ruicheng Xian

DenseNets introduce concatenation-type skip connections that achieve state-of-the-art accuracy in several computer vision tasks. In this paper, we reveal that the topology of the concatenation-type skip connections is closely related to the…

Machine Learning · Statistics 2021-04-02 Kartikeya Bhardwaj , Guihong Li , Radu Marculescu

Deep neural networks have a good success record and are thus viewed as the best architecture choice for complex applications. Their main shortcoming has been, for a long time, the vanishing gradient which prevented the numerical…

Machine Learning · Computer Science 2024-05-02 Bernhard Bermeitinger , Tomas Hrycej , Siegfried Handschuh

Whilst deep neural networks have shown great empirical success, there is still much work to be done to understand their theoretical properties. In this paper, we study the relationship between random, wide, fully connected, feedforward…

Machine Learning · Statistics 2018-08-17 Alexander G. de G. Matthews , Mark Rowland , Jiri Hron , Richard E. Turner , Zoubin Ghahramani

We investigate the asymptotic properties of deep Residual networks (ResNets) as the number of layers increases. We first show the existence of scaling regimes for trained weights markedly different from those implicitly assumed in the…

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

Motivated by both theory and practice, we study how random pruning of the weights affects a neural network's neural tangent kernel (NTK). In particular, this work establishes an equivalence of the NTKs between a fully-connected neural…

Machine Learning · Computer Science 2023-03-21 Hongru Yang , Zhangyang Wang

The trend towards increasingly deep neural networks has been driven by a general observation that increasing depth increases the performance of a network. Recently, however, evidence has been amassing that simply increasing depth may not be…

Computer Vision and Pattern Recognition · Computer Science 2016-12-01 Zifeng Wu , Chunhua Shen , Anton van den Hengel

Infinite width limits of deep neural networks often have tractable forms. They have been used to analyse the behaviour of finite networks, as well as being useful methods in their own right. When investigating infinitely wide convolutional…

Machine Learning · Statistics 2021-06-15 Adrià Garriga-Alonso , Mark van der Wilk

We study the following paradox associated with networks growing according to superlinear preferential attachment: superlinear preference cannot produce scale-free networks in the thermodynamic limit, but there are superlinearly growing…

Statistical Mechanics · Physics 2008-08-23 Paul Krapivsky , Dmitri Krioukov

We explore the link between deep ensembles and Gaussian processes (GPs) through the lens of the Neural Tangent Kernel (NTK): a recent development in understanding the training dynamics of wide neural networks (NNs). Previous work has shown…

Machine Learning · Statistics 2020-10-27 Bobby He , Balaji Lakshminarayanan , Yee Whye Teh

Scaling limits, such as infinite-width limits, serve as promising theoretical tools to study large-scale models. However, it is widely believed that existing infinite-width theory does not faithfully explain the behavior of practical…

Machine Learning · Computer Science 2025-10-28 Moritz Haas , Sebastian Bordt , Ulrike von Luxburg , Leena Chennuru Vankadara

Deep Gaussian Process (DGP) as a model prior in Bayesian learning intuitively exploits the expressive power in function composition. DGPs also offer diverse modeling capabilities, but inference is challenging because marginalization in…

Machine Learning · Computer Science 2022-08-02 Chi-Ken Lu , Patrick Shafto

The classical Universal Approximation Theorem holds for neural networks of arbitrary width and bounded depth. Here we consider the natural `dual' scenario for networks of bounded width and arbitrary depth. Precisely, let $n$ be the number…

Machine Learning · Computer Science 2020-06-09 Patrick Kidger , Terry Lyons