English
Related papers

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

200 papers

Deep neural networks have achieved remarkable success in practice, yet a mechanistic understanding of how features evolve during training remains incomplete, especially in the large-depth limit. For ResNets under depth-$\mu$P scaling, prior…

Machine Learning · Computer Science 2026-05-28 Zihan Yao , Ruoyu Wu , Tianxiang Gao

Comparing Bayesian neural networks (BNNs) with different widths is challenging because, as the width increases, multiple model properties change simultaneously, and, inference in the finite-width case is intractable. In this work, we…

Machine Learning · Statistics 2022-11-29 Jiayu Yao , Yaniv Yacoby , Beau Coker , Weiwei Pan , Finale Doshi-Velez

We provide quantitative bounds measuring the $L^2$ difference in function space between the trajectory of a finite-width network trained on finitely many samples from the idealized kernel dynamics of infinite width and infinite data. An…

Machine Learning · Statistics 2022-10-18 Benjamin Bowman , Guido Montufar

We give a proof that, under relatively mild conditions, fully-connected feed-forward deep random neural networks converge to a Gaussian mixture distribution as only the width of the last hidden layer goes to infinity. We conducted…

Machine Learning · Statistics 2022-04-27 Yasuhiko Asao , Ryotaro Sakamoto , Shiro Takagi

In this work we propose a novel interpretation of residual networks showing that they can be seen as a collection of many paths of differing length. Moreover, residual networks seem to enable very deep networks by leveraging only the short…

Computer Vision and Pattern Recognition · Computer Science 2016-10-28 Andreas Veit , Michael Wilber , Serge Belongie

Deep linear networks have been extensively studied, as they provide simplified models of deep learning. However, little is known in the case of finite-width architectures with multiple outputs and convolutional layers. In this manuscript,…

Machine Learning · Statistics 2025-06-26 Federico Bassetti , Marco Gherardi , Alessandro Ingrosso , Mauro Pastore , Pietro Rotondo

A key property of neural networks driving their success is their ability to learn features from data. Understanding feature learning from a theoretical viewpoint is an emerging field with many open questions. In this work we capture…

Disordered Systems and Neural Networks · Physics 2024-05-20 Kirsten Fischer , Javed Lindner , David Dahmen , Zohar Ringel , Michael Krämer , Moritz Helias

Contemporary deep neural networks exhibit impressive results on practical problems. These networks generalize well although their inherent capacity may extend significantly beyond the number of training examples. We analyze this behavior in…

Machine Learning · Computer Science 2015-09-03 Tamir Hazan , Tommi Jaakkola

We study the effect of width on the dynamics of feature-learning neural networks across a variety of architectures and datasets. Early in training, wide neural networks trained on online data have not only identical loss curves but also…

Machine Learning · Computer Science 2023-12-07 Nikhil Vyas , Alexander Atanasov , Blake Bordelon , Depen Morwani , Sabarish Sainathan , Cengiz Pehlevan

Existing work has linked properties of a function's gradient to the difficulty of function approximation. Motivated by these insights, we study how gradient information can be leveraged to improve neural network's ability to approximate…

Machine Learning · Computer Science 2026-02-11 Yangchen Pan , Qizhen Ying , Philip Torr , Bo Liu

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

We introduce a design strategy for neural network macro-architecture based on self-similarity. Repeated application of a simple expansion rule generates deep networks whose structural layouts are precisely truncated fractals. These networks…

Computer Vision and Pattern Recognition · Computer Science 2017-05-30 Gustav Larsson , Michael Maire , Gregory Shakhnarovich

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

This work theoretically studies stochastic neural networks, a main type of neural network in use. We prove that as the width of an optimized stochastic neural network tends to infinity, its predictive variance on the training set decreases…

Machine Learning · Computer Science 2022-05-25 Liu Ziyin , Hanlin Zhang , Xiangming Meng , Yuting Lu , Eric Xing , Masahito Ueda

A recurrent neural network (RNN) is a widely used deep-learning network for dealing with sequential data. Imitating a dynamical system, an infinite-width RNN can approximate any open dynamical system in a compact domain. In general, deep…

Machine Learning · Statistics 2023-03-30 Chang hoon Song , Geonho Hwang , Jun ho Lee , Myungjoo Kang

We study shallow and deep neural networks whose inputs range over a general topological space. The model is built from a prescribed family of continuous feature maps and reduces to multilayer feedforward networks in the Euclidean case. We…

General Topology · Mathematics 2026-03-24 Vugar Ismailov

A key attribute that drives the unprecedented success of modern Recurrent Neural Networks (RNNs) on learning tasks which involve sequential data, is their ability to model intricate long-term temporal dependencies. However, a well…

Machine Learning · Computer Science 2018-06-07 Yoav Levine , Or Sharir , Alon Ziv , Amnon Shashua

A long-standing obstacle to progress in deep learning is the problem of vanishing and exploding gradients. Although, the problem has largely been overcome via carefully constructed initializations and batch normalization, architectures…

Neural and Evolutionary Computing · Computer Science 2018-06-07 David Balduzzi , Marcus Frean , Lennox Leary , JP Lewis , Kurt Wan-Duo Ma , Brian McWilliams

Scaling up network depth is a fundamental pursuit in neural architecture design, as theory suggests that deeper models offer exponentially greater capability. Benefiting from the residual connections, modern neural networks can scale up to…

Computer Vision and Pattern Recognition · Computer Science 2025-11-19 Dongchen Han , Tianzhu Ye , Zhuofan Xia , Kaiyi Chen , Yulin Wang , Hanting Chen , Gao Huang

Residual connections remain ubiquitous in modern neural network architectures nearly a decade after their introduction. Their widespread adoption is often credited to their dramatically improved trainability: residual networks train faster,…

Machine Learning · Computer Science 2025-06-18 Christian H. X. Ali Mehmeti-Göpel , Michael Wand
‹ Prev 1 4 5 6 7 8 10 Next ›