中文
相关论文

相关论文: Architecture independent generalization bounds for…

200 篇论文

Recurrent Neural Networks (RNNs) have been widely applied to sequential data analysis. Due to their complicated modeling structures, however, the theory behind is still largely missing. To connect theory and practice, we study the…

机器学习 · 计算机科学 2019-11-05 Minshuo Chen , Xingguo Li , Tuo Zhao

Explaining the unreasonable effectiveness of deep learning has eluded researchers around the globe. Various authors have described multiple metrics to evaluate the capacity of deep architectures. In this paper, we allude to the radius…

机器学习 · 计算机科学 2018-11-06 Mayank Sharma , Jayadeva , Sumit Soman

{\em Hypernetworks} are architectures that produce the weights of a task-specific {\em primary network}. A notable application of hypernetworks in the recent literature involves learning to output functional representations. In these…

机器学习 · 计算机科学 2021-02-24 Etai Littwin , Tomer Galanti , Lior Wolf , Greg Yang

In this paper, we investigate the Rademacher complexity of deep sparse neural networks, where each neuron receives a small number of inputs. We prove generalization bounds for multilayered sparse ReLU neural networks, including…

机器学习 · 计算机科学 2023-01-31 Tomer Galanti , Mengjia Xu , Liane Galanti , Tomaso Poggio

We consider training over-parameterized two-layer neural networks with Rectified Linear Unit (ReLU) using gradient descent (GD) method. Inspired by a recent line of work, we study the evolutions of network prediction errors across GD…

机器学习 · 计算机科学 2019-09-04 Lili Su , Pengkun Yang

We theoretically demonstrate that the generalization error of interpolators for machine learning models under teacher-student settings becomes 0 once the number of training samples exceeds a certain threshold. Understanding the high…

机器学习 · 计算机科学 2025-12-09 Naoki Yoshida , Isao Ishikawa , Masaaki Imaizumi

Deep neural networks are often trained in the over-parametrized regime (i.e. with far more parameters than training examples), and understanding why the training converges to solutions that generalize remains an open problem. Several…

机器学习 · 统计学 2018-03-23 Hartmut Maennel , Olivier Bousquet , Sylvain Gelly

Neural networks typically generalize well when fitting the data perfectly, even though they are heavily overparameterized. Many factors have been pointed out as the reason for this phenomenon, including an implicit bias of stochastic…

机器学习 · 计算机科学 2025-02-04 Amit Peleg , Matthias Hein

It is frequently observed that overparameterized neural networks generalize well. Regarding such phenomena, existing theoretical work mainly devotes to linear settings or fully-connected neural networks. This paper studies the learning…

机器学习 · 统计学 2023-08-17 Tian-Yi Zhou , Xiaoming Huo

Recurrent Neural Network (RNN) is a fundamental structure in deep learning. Recently, some works study the training process of over-parameterized neural networks, and show that over-parameterized networks can learn functions in some notable…

机器学习 · 计算机科学 2022-01-27 Lifu Wang , Bo Shen , Bo Hu , Xing Cao

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…

机器学习 · 统计学 2024-07-02 Gholamali Aminian , Yixuan He , Gesine Reinert , Łukasz Szpruch , Samuel N. Cohen

We study the generalization of over-parameterized deep networks (for image classification) in relation to the convex hull of their training sets. Despite their great success, generalization of deep networks is considered a mystery. These…

机器学习 · 计算机科学 2022-03-22 Roozbeh Yousefzadeh

We study the overparametrization bounds required for the global convergence of stochastic gradient descent algorithm for a class of one hidden layer feed-forward neural networks, considering most of the activation functions used in…

机器学习 · 计算机科学 2022-11-17 Bartłomiej Polaczyk , Jacek Cyranka

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…

机器学习 · 计算机科学 2022-06-08 Peng He

Deep neural networks (DNNs) have demonstrated dominating performance in many fields; since AlexNet, networks used in practice are going wider and deeper. On the theoretical side, a long line of works has been focusing on training neural…

机器学习 · 计算机科学 2019-06-18 Zeyuan Allen-Zhu , Yuanzhi Li , Zhao Song

Largest theoretical contribution to Neural Networks comes from VC Dimension which characterizes the sample complexity of classification model in a probabilistic view and are widely used to study the generalization error. So far in the…

机器学习 · 计算机科学 2024-09-05 Linu Pinto , Sasi Gopalan

We derive generalization error bounds for the training of two-layer neural networks without assuming boundedness of the loss function, using Wasserstein distance estimates on the discrepancy between a probability distribution and its…

机器学习 · 统计学 2026-04-09 Jiang Yu Nguwi , Nicolas Privault

In this paper, we study the generalization performance of global minima for implementing empirical risk minimization (ERM) on over-parameterized deep ReLU nets. Using a novel deepening scheme for deep ReLU nets, we rigorously prove that…

机器学习 · 计算机科学 2023-03-01 Shao-Bo Lin , Yao Wang , Ding-Xuan Zhou

The generalization error of deep neural networks via their classification margin is studied in this work. Our approach is based on the Jacobian matrix of a deep neural network and can be applied to networks with arbitrary non-linearities…

机器学习 · 统计学 2017-07-04 Jure Sokolic , Raja Giryes , Guillermo Sapiro , Miguel R. D. Rodrigues

Deep learning methods minimise the empirical risk using loss functions such as the cross entropy loss. When minimising the empirical risk, the generalisation of the learnt function still depends on the performance on the training data, the…

机器学习 · 计算机科学 2022-01-19 Antonio Jimeno Yepes