English
Related papers

Related papers: Depthwise Hyperparameter Transfer in Residual Netw…

200 papers

We study the convergence of gradient flow for the training of deep neural networks. If Residual Neural Networks are a popular example of very deep architectures, their training constitutes a challenging optimization problem due notably to…

Machine Learning · Computer Science 2025-07-22 Raphaël Barboni , Gabriel Peyré , François-Xavier Vialard

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

Local learning, which trains a network through layer-wise local targets and losses, has been studied as an alternative to backpropagation (BP) in neural computation. However, its algorithms often become more complex or require additional…

Machine Learning · Computer Science 2025-05-22 Satoki Ishikawa , Rio Yokota , Ryo Karakida

Deep learning has been successful in automating the design of features in machine learning pipelines. However, the algorithms optimizing neural network parameters remain largely hand-designed and computationally inefficient. We study if we…

Machine Learning · Computer Science 2021-10-26 Boris Knyazev , Michal Drozdzal , Graham W. Taylor , Adriana Romero-Soriano

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

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

Various architectures (such as GoogLeNets, ResNets, and DenseNets) have been proposed. However, the existing networks usually suffer from either redundancy of convolutional layers or insufficient utilization of parameters. To handle these…

Computer Vision and Pattern Recognition · Computer Science 2020-04-27 Zhiyu Zhu , Zhen-Peng Bian , Junhui Hou , Yi Wang , Lap-Pui Chau

Modern large-scale neural networks are often trained and released in multiple sizes to accommodate diverse inference budgets. To improve efficiency, recent work has explored model upscaling: initializing larger models from trained smaller…

Machine Learning · Computer Science 2026-02-12 Yuxin Ma , Nan Chen , Mateo Díaz , Soufiane Hayou , Dmitriy Kunisky , Soledad Villar

Structured pruning compresses neural networks by reducing channels (filters) for fast inference and low footprint at run-time. To restore accuracy after pruning, fine-tuning is usually applied to pruned networks. However, too few remaining…

Computer Vision and Pattern Recognition · Computer Science 2024-01-01 Yu Qian , Jian Cao , Xiaoshuang Li , Jie Zhang , Hufei Li , Jue Chen

In this work, we analyze various scaling limits of the training dynamics of transformer models in the feature learning regime. We identify the set of parameterizations that admit well-defined infinite width and depth limits, allowing the…

Machine Learning · Statistics 2024-10-07 Blake Bordelon , Hamza Tahir Chaudhry , Cengiz Pehlevan

Recent works show that overparameterized networks contain small subnetworks that exhibit comparable accuracy to the full model when trained in isolation. These results highlight the potential to reduce training costs of deep neural networks…

Machine Learning · Computer Science 2020-06-25 Roger Waleffe , Theodoros Rekatsinas

Deep residual networks were shown to be able to scale up to thousands of layers and still have improving performance. However, each fraction of a percent of improved accuracy costs nearly doubling the number of layers, and so training very…

Computer Vision and Pattern Recognition · Computer Science 2017-06-15 Sergey Zagoruyko , Nikos Komodakis

We present a novel optimization strategy for training neural networks which we call "BitNet". The parameters of neural networks are usually unconstrained and have a dynamic range dispersed over all real values. Our key idea is to limit the…

Machine Learning · Computer Science 2018-11-20 Aswin Raghavan , Mohamed Amer , Sek Chai , Graham Taylor

This paper proposes a new mean-field framework for over-parameterized deep neural networks (DNNs), which can be used to analyze neural network training. In this framework, a DNN is represented by probability measures and functions over its…

Machine Learning · Statistics 2020-07-06 Cong Fang , Jason D. Lee , Pengkun Yang , Tong Zhang

For almost 70 years, researchers have typically selected the width of neural networks' layers either manually or through automated hyperparameter tuning methods such as grid search and, more recently, neural architecture search. This paper…

Machine Learning · Computer Science 2026-02-17 Federico Errica , Henrik Christiansen , Viktor Zaverkin , Mathias Niepert , Francesco Alesiani

We rigorously evaluate three state-of-the-art techniques for inducing sparsity in deep neural networks on two large-scale learning tasks: Transformer trained on WMT 2014 English-to-German, and ResNet-50 trained on ImageNet. Across thousands…

Machine Learning · Computer Science 2019-02-27 Trevor Gale , Erich Elsen , Sara Hooker

Modern deep neural networks are highly over-parameterized compared to the data on which they are trained, yet they often generalize remarkably well. A flurry of recent work has asked: why do deep networks not overfit to their training data?…

Machine Learning · Computer Science 2023-03-24 Minyoung Huh , Hossein Mobahi , Richard Zhang , Brian Cheung , Pulkit Agrawal , Phillip Isola

How to reduce the requirement on training dataset size is a hot topic in deep learning community. One straightforward way is to reuse some pre-trained parameters. Some previous work like Deep transfer learning reuse the model parameters…

Computer Vision and Pattern Recognition · Computer Science 2020-09-21 Wei Wang

Overparameterized neural networks enjoy great representation power on complex data, and more importantly yield sufficiently smooth output, which is crucial to their generalization and robustness. Most existing function approximation…

Machine Learning · Statistics 2022-06-10 Hao Liu , Minshuo Chen , Siawpeng Er , Wenjing Liao , Tong Zhang , Tuo Zhao

A recent line of research on deep learning focuses on the extremely over-parameterized setting, and shows that when the network width is larger than a high degree polynomial of the training sample size $n$ and the inverse of the target…

Machine Learning · Computer Science 2022-01-03 Zixiang Chen , Yuan Cao , Difan Zou , Quanquan Gu