English
Related papers

Related papers: Scaling ResNets in the Large-depth Regime

200 papers

Reinforcement Learning (RL) for training Large Language Models is notoriously unstable. While recent studies attribute this to "training inference mismatch stemming" from inconsistent hybrid engines, standard remedies, such as Importance…

Machine Learning · Computer Science 2026-02-03 Yaxiang Zhang , Yingru Li , Jiacai Liu , Jiawei Xu , Ziniu Li , Qian Liu , Haoyuan Li

We study multigrade deep learning (MGDL) as a principled framework for structured error refinement in deep neural networks. While the approximation power of neural networks is now relatively well understood, training very deep architectures…

Machine Learning · Computer Science 2026-04-03 Shijun Zhang , Zuowei Shen , Yuesheng Xu

We analyze the input-output behavior of residual networks from a dynamical system point of view by disentangling the residual dynamics from the output activities before the classification stage. For a network with simple skip connections…

Computer Vision and Pattern Recognition · Computer Science 2021-05-12 Fereshteh Lagzi

In-context learning (ICL) enables large language models to adapt to new tasks from demonstrations without parameter updates. Despite extensive empirical studies, a principled understanding of ICL emergence at scale remains more elusive. We…

Machine Learning · Computer Science 2025-11-11 Sushant Mehta , Ishan Gupta

Large language model (LLM) scaling is hitting a wall. Widening models yields diminishing returns, and extending context length does not improve fundamental expressivity. In contrast, depth scaling offers theoretically superior expressivity,…

Machine Learning · Computer Science 2026-02-02 Chen Chen , Lai Wei

We analyze multi-layer neural networks in the asymptotic regime of simultaneously (A) large network sizes and (B) large numbers of stochastic gradient descent training iterations. We rigorously establish the limiting behavior of the…

Probability · Mathematics 2021-04-06 Justin Sirignano , Konstantinos Spiliopoulos

Large language models (LLMs) often struggle with strict memory, latency, and power demands. To meet these demands, various forms of dynamic sparsity have been proposed that reduce compute on an input-by-input basis. These methods improve…

Computation and Language · Computer Science 2024-04-09 Jordan Dotzel , Yash Akhauri , Ahmed S. AbouElhamayed , Carly Jiang , Mohamed Abdelfattah , Zhiru Zhang

Deep networks often suffer from vanishing or exploding gradients due to inefficient signal propagation, leading to long training times or convergence difficulties. Various architecture designs, sophisticated residual-style networks, and…

Recurrent Neural Networks (RNNs) are widely used for modelling neural activity, yet the mathematical interplay of core procedures is used to analyze them (temporal rescaling, discretization, and linearization) remain uncharacterized. This…

Neural and Evolutionary Computing · Computer Science 2025-04-08 Mariano Caruso , Cecilia Jarne

Recent work has studied the reasons for the remarkable performance of deep neural networks in image classification. We examine batch normalization on the one hand and the dynamical systems view of residual networks on the other hand. Our…

Machine Learning · Computer Science 2018-10-02 Jingfeng Zhang , Laura Wynter

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 2020-03-24 Alon Ziv

The Wide Residual Networks (Wide-ResNets), a shallow but wide model variant of the Residual Networks (ResNets) by stacking a small number of residual blocks with large channel sizes, have demonstrated outstanding performance on multiple…

Computer Vision and Pattern Recognition · Computer Science 2021-02-09 Liang-Chieh Chen , Huiyu Wang , Siyuan Qiao

Deep learning is recognized to be capable of discovering deep features for representation learning and pattern recognition without requiring elegant feature engineering techniques by taking advantage of human ingenuity and prior knowledge.…

Machine Learning · Computer Science 2020-04-02 Zhi Han , Siquan Yu , Shao-Bo Lin , Ding-Xuan Zhou

Deep neural networks are powerful tools for solving nonlinear problems in science and engineering, but training highly accurate models becomes challenging as problem complexity increases. Non-convex optimization and sensitivity to…

Machine Learning · Computer Science 2026-04-20 Ethan Mulle , Wei Kang , Qi Gong

Various powerful deep neural network architectures have made great contribution to the exciting successes of deep learning in the past two decades. Among them, deep Residual Networks (ResNets) are of particular importance because they…

Machine Learning · Computer Science 2022-05-16 Wentao Huang , Haizhang Zhang

Several recent trends in machine learning theory and practice, from the design of state-of-the-art Gaussian Process to the convergence analysis of deep neural nets (DNNs) under stochastic gradient descent (SGD), have found it fruitful to…

Neural and Evolutionary Computing · Computer Science 2020-04-07 Greg Yang

Skip connection, is a widely-used technique to improve the performance and the convergence of deep neural networks, which is believed to relieve the difficulty in optimization due to non-linearity by propagating a linear component through…

Machine Learning · Computer Science 2021-05-18 Fenglin Liu , Xuancheng Ren , Zhiyuan Zhang , Xu Sun , Yuexian Zou

Deep architectures consist of tens or hundreds of convolutional layers (CLs) that terminate with a few fully connected (FC) layers and an output layer representing the possible labels of a complex classification task. According to the…

Computer Vision and Pattern Recognition · Computer Science 2023-05-30 Yarden Tzach , Yuval Meir , Ofek Tevet , Ronit D. Gross , Shiri Hodassman , Roni Vardi , Ido Kanter

An emerging design principle in deep learning is that each layer of a deep artificial neural network should be able to easily express the identity transformation. This idea not only motivated various normalization techniques, such as…

Machine Learning · Computer Science 2018-07-23 Moritz Hardt , Tengyu Ma

This paper presents a simple yet principled approach to boosting the robustness of the residual network (ResNet) that is motivated by the dynamical system perspective. Namely, a deep neural network can be interpreted using a partial…

Computer Vision and Pattern Recognition · Computer Science 2019-07-03 Jingfeng Zhang , Bo Han , Laura Wynter , Kian Hsiang Low , Mohan Kankanhalli
‹ Prev 1 4 5 6 7 8 10 Next ›