English
Related papers

Related papers: Why do Larger Models Generalize Better? A Theoreti…

200 papers

This work provides a theoretical framework for assessing the generalization error of graph neural networks in the over-parameterized regime, where the number of parameters surpasses the quantity of data points. We explore two widely…

Machine Learning · Statistics 2024-07-02 Gholamali Aminian , Yixuan He , Gesine Reinert , Łukasz Szpruch , Samuel N. Cohen

Previous theoretical work on deep learning and neural network optimization tend to focus on avoiding saddle points and local minima. However, the practical observation is that, at least in the case of the most successful Deep Convolutional…

Machine Learning · Computer Science 2017-06-23 Qianli Liao , Tomaso Poggio

Deep neural networks generalize well despite being exceedingly overparameterized and being trained without explicit regularization. This curious phenomenon has inspired extensive research activity in establishing its statistical principles:…

Machine Learning · Statistics 2021-09-16 Ke Wang , Christos Thrampoulidis

Gradient descent on overparameterized neural networks typically operates at the Edge of Stability (EoS), where the largest Hessian eigenvalue hovers around a step-size-dependent threshold. We study how sparse connectivity changes…

Machine Learning · Statistics 2026-05-08 Tongtong Liang , Esha Singh , Rahul Parhi , Alexander Cloninger , Yu-Xiang Wang

A practical limitation of deep neural networks is their high degree of specialization to a single task and visual domain. Recently, inspired by the successes of transfer learning, several authors have proposed to learn instead universal,…

Computer Vision and Pattern Recognition · Computer Science 2018-03-28 Sylvestre-Alvise Rebuffi , Hakan Bilen , Andrea Vedaldi

This theoretical paper is devoted to developing a rigorous theory for demystifying the global convergence phenomenon in a challenging scenario: learning over-parameterized Rectified Linear Unit (ReLU) nets for very high dimensional dataset…

Machine Learning · Computer Science 2022-06-08 Peng He

Analysis of over-parameterized neural networks has drawn significant attention in recentyears. It was shown that such systems behave like convex systems under various restrictedsettings, such as for two-level neural networks, and when…

Machine Learning · Computer Science 2019-11-19 Cong Fang , Yihong Gu , Weizhong Zhang , Tong Zhang

We theoretically study the landscape of the training error for neural networks in overparameterized cases. We consider three basic methods for embedding a network into a wider one with more hidden units, and discuss whether a minimum point…

Machine Learning · Computer Science 2019-06-17 Kenji Fukumizu , Shoichiro Yamaguchi , Yoh-ichi Mototake , Mirai Tanaka

This paper proposes a novel regularization approach to bias Convolutional Neural Networks (CNNs) toward utilizing edge and line features in their hidden layers. Rather than learning arbitrary kernels, we constrain the convolution layers to…

Computer Vision and Pattern Recognition · Computer Science 2024-10-23 Christoph Linse , Beatrice Brückner , Thomas Martinetz

Aimed at explaining the surprisingly good generalization behavior of overparameterized deep networks, recent works have developed a variety of generalization bounds for deep learning, all based on the fundamental learning-theoretic…

Machine Learning · Computer Science 2021-10-19 Vaishnavh Nagarajan , J. Zico Kolter

Compact neural network offers many benefits for real-world applications. However, it is usually challenging to train the compact neural networks with small parameter sizes and low computational costs to achieve the same or better model…

Machine Learning · Computer Science 2023-08-28 Shen Ren , Haosen Shi

When training overparameterized deep networks for classification tasks, it has been widely observed that the learned features exhibit a so-called "neural collapse" phenomenon. More specifically, for the output features of the penultimate…

Machine Learning · Computer Science 2023-03-09 Can Yaras , Peng Wang , Zhihui Zhu , Laura Balzano , Qing Qu

Large neural networks are heavily over-parameterized. This is done because it improves training to optimality. However once the network is trained, this means many parameters can be zeroed, or pruned, leaving an equivalent sparse neural…

Machine Learning · Computer Science 2022-07-12 Michael G. Rawson

Modern deep learning models employ considerably more parameters than required to fit the training data. Whereas conventional statistical wisdom suggests such models should drastically overfit, in practice these models generalize remarkably…

Machine Learning · Statistics 2020-08-18 Ben Adlam , Jeffrey Pennington

While normalization techniques are widely used in deep learning, their theoretical understanding remains relatively limited. In this work, we establish the benefits of (generalized) weight normalization (WN) applied to the overparameterized…

Machine Learning · Computer Science 2025-10-02 Yudong Wei , Liang Zhang , Bingcong Li , Niao He

We study regularization in the context of small sample-size learning with over-parameterized neural networks. Specifically, we shift focus from architectural properties, such as norms on the network weights, to properties of the internal…

Machine Learning · Computer Science 2021-05-18 Christoph D. Hofer , Florian Graf , Marc Niethammer , Roland Kwitt

Distributed learning facilitates the scaling-up of data processing by distributing the computational burden over several nodes. Despite the vast interest in distributed learning, generalization performance of such approaches is not well…

Machine Learning · Statistics 2020-05-05 Martin Hellkvist , Ayça Özçelikkale , Anders Ahlén

Fully convolutional neural networks can process input of arbitrary size by applying a combination of downsampling and pooling. However, we find that fully convolutional image classifiers are not agnostic to the input size but rather show…

Machine Learning · Computer Science 2021-10-13 Mats L. Richter , Wolf Byttner , Ulf Krumnack , Ludwdig Schallner , Justin Shenk

We analyze single-layer neural networks with the Xavier initialization in the asymptotic regime of large numbers of hidden units and large numbers of stochastic gradient descent training steps. The evolution of the neural network during…

Probability · Mathematics 2022-04-13 Justin Sirignano , Konstantinos Spiliopoulos

Currently, increasingly deeper neural networks have been applied to improve their accuracy. In contrast, We propose a novel wider Convolutional Neural Networks (CNN) architecture, motivated by the Multi-column Deep Neural Networks and the…

Computer Vision and Pattern Recognition · Computer Science 2018-10-10 Xiaobo Huang