English
Related papers

Related papers: Expected Gradients of Maxout Networks and Conseque…

200 papers

Dropout is a standard training technique for neural networks that consists of randomly deactivating units at each step of their gradient-based training. It is known to improve performance in many settings, including in the large-scale…

Machine Learning · Computer Science 2025-10-10 Lénaïc Chizat , Pierre Marion , Yerkin Yesbay

The weight initialization and the activation function of deep neural networks have a crucial impact on the performance of the training procedure. An inappropriate selection can lead to the loss of information of the input during forward…

Machine Learning · Statistics 2019-05-28 Soufiane Hayou , Arnaud Doucet , Judith Rousseau

We theoretically characterize gradient descent dynamics in deep linear networks trained at large width from random initialization and on large quantities of random data. Our theory captures the ``wider is better" effect of…

Machine Learning · Computer Science 2025-06-17 Blake Bordelon , Cengiz Pehlevan

The regularization and output consistency behavior of dropout and layer-wise pretraining for learning deep networks have been fairly well studied. However, our understanding of how the asymptotic convergence of backpropagation in deep…

Machine Learning · Computer Science 2017-02-23 Vamsi K Ithapu , Sathya N Ravi , Vikas Singh

Recent work has shown that tight concentration of the entire spectrum of singular values of a deep network's input-output Jacobian around one at initialization can speed up learning by orders of magnitude. Therefore, to guide important…

Machine Learning · Statistics 2018-02-28 Jeffrey Pennington , Samuel S. Schoenholz , Surya Ganguli

The principle of maximum entropy (Maxent) is often used to obtain prior probability distributions as a method to obtain a Gibbs measure under some restriction giving the probability that a system will be in a certain state compared to the…

Information Theory · Computer Science 2019-06-26 Hector Zenil , Narsis A. Kiani , Jesper Tegnér

Innovations in neural architectures have fostered significant breakthroughs in language modeling and computer vision. Unfortunately, novel architectures often result in challenging hyper-parameter choices and training instability if the…

Machine Learning · Computer Science 2021-11-25 Chen Zhu , Renkun Ni , Zheng Xu , Kezhi Kong , W. Ronny Huang , Tom Goldstein

Training neural networks via backpropagation is often hindered by vanishing or exploding gradients. In this work, we design architectures that mitigate these issues by analyzing and controlling the network Jacobian. We first provide a…

Machine Learning · Computer Science 2026-02-12 Alex Massucco , Davide Murari , Carola-Bibiane Schönlieb

Unsupervised pretraining and dropout have been well studied, especially with respect to regularization and output consistency. However, our understanding about the explicit convergence rates of the parameter estimates, and their dependence…

Machine Learning · Computer Science 2017-02-23 Vamsi K. Ithapu , Sathya Ravi , Vikas Singh

We investigate the convergence and convergence rate of stochastic training algorithms for Neural Networks (NNs) that have been inspired by Dropout (Hinton et al., 2012). With the goal of avoiding overfitting during training of NNs, dropout…

Optimization and Control · Mathematics 2023-03-24 Albert Senen-Cerda , Jaron Sanders

When an online learning algorithm is used to estimate the unknown parameters of a model, the signals interacting with the parameter estimates should not decay too quickly for the optimal values to be discovered correctly. This requirement…

Machine Learning · Computer Science 2019-11-05 Kamil Nar , S. Shankar Sastry

We study the training and generalization of deep neural networks (DNNs) in the over-parameterized regime, where the network width (i.e., number of hidden nodes per layer) is much larger than the number of training data points. We show that,…

Machine Learning · Computer Science 2019-11-13 Yuan Cao , Quanquan Gu

The massive size of modern neural networks has motivated substantial recent interest in neural network quantization. We introduce Stochastic Markov Gradient Descent (SMGD), a discrete optimization method applicable to training quantized…

Machine Learning · Computer Science 2020-12-23 Jonathan Ashbrock , Alexander M. Powell

The skip-connections used in residual networks have become a standard architecture choice in deep learning due to the increased training stability and generalization performance with this architecture, although there has been limited…

Machine Learning · Computer Science 2019-10-08 Spencer Frei , Yuan Cao , Quanquan Gu

To theoretically understand the behavior of trained deep neural networks, it is necessary to study the dynamics induced by gradient methods from a random initialization. However, the nonlinear and compositional structure of these models…

Machine Learning · Computer Science 2021-12-21 Karl Hajjar , Lénaïc Chizat , Christophe Giraud

Neural networks trained via gradient descent with random initialization and without any regularization enjoy good generalization performance in practice despite being highly overparametrized. A promising direction to explain this phenomenon…

Machine Learning · Computer Science 2022-05-17 Hancheng Min , Salma Tarmoun , Rene Vidal , Enrique Mallada

Vanishing (and exploding) gradients effect is a common problem for recurrent neural networks with nonlinear activation functions which use backpropagation method for calculation of derivatives. Deep feedforward neural networks with many…

Neural and Evolutionary Computing · Computer Science 2017-02-15 Artem Chernodub , Dimitri Nowicki

Tensor networks have demonstrated significant value for machine learning in a myriad of different applications. However, optimizing tensor networks using standard gradient descent has proven to be difficult in practice. Tensor networks…

Machine Learning · Computer Science 2022-03-08 Fergus Barratt , James Dborin , Lewis Wright

In this work, we propose to employ information-geometric tools to optimize a graph neural network architecture such as the graph convolutional networks. More specifically, we develop optimization algorithms for the graph-based…

Machine Learning · Computer Science 2020-08-25 Mohammad Rasool Izadi , Yihao Fang , Robert Stevenson , Lizhen Lin

Natural gradient descent has proven effective at mitigating the effects of pathological curvature in neural network optimization, but little is known theoretically about its convergence properties, especially for \emph{nonlinear} networks.…

Machine Learning · Statistics 2019-10-29 Guodong Zhang , James Martens , Roger Grosse