English
Related papers

Related papers: Stabilizing Gradients for Deep Neural Networks via…

200 papers

The state-of-the-art deep neural networks (DNNs) have significant computational and data management requirements. The size of both training data and models continue to increase. Sparsification and pruning methods are shown to be effective…

Machine Learning · Computer Science 2021-04-27 Gunduz Vehbi Demirci , Hakan Ferhatosmanoglu

Recurrent neural networks (RNNs) are notoriously difficult to train. When the eigenvalues of the hidden to hidden weight matrix deviate from absolute value 1, optimization becomes difficult due to the well studied issue of vanishing and…

Machine Learning · Computer Science 2016-10-13 Martin Arjovsky , Amar Shah , Yoshua Bengio

Recurrent neural networks (RNNs) have recently demonstrated strong performance and faster inference than Transformers at comparable parameter budgets. However, the recursive gradient computation with the backpropagation through time (or…

Machine Learning · Computer Science 2025-04-01 Paul Caillon , Erwan Fagnou , Alexandre Allauzen

Singular Value Decomposition (SVD) is a powerful tool for multivariate analysis. However, independent computation of the SVD for each sample taken from a bandlimited matrix random process will result in singular value sample paths whose…

Statistics Theory · Mathematics 2007-06-13 D. W. Browne , M. W. Browne , M. P. Fitz

Random-feature neural networks (RFNNs), including architectures with fixed hidden layers and analytically determined output weights, offer fast training but often suffer from issues due to dense representations of the hidden layer…

Numerical Analysis · Mathematics 2026-05-11 Kevin Kurian Thomas Vaidyan , Siddharth Rout

A Recurrent Neural Network (RNN) for Video Super Resolution (VSR) is generally trained with randomly clipped and cropped short videos extracted from original training videos due to various challenges in learning RNNs. However, since this…

Computer Vision and Pattern Recognition · Computer Science 2024-03-26 Hiroshi Mori , Norimichi Ukita

A recent strategy to circumvent the exploding and vanishing gradient problem in RNNs, and to allow the stable propagation of signals over long time scales, is to constrain recurrent connectivity matrices to be orthogonal or unitary. This…

Singular value decomposition (SVD) is one of the most popular compression methods that approximate a target matrix with smaller matrices. However, standard SVD treats the parameters within the matrix with equal importance, which is a simple…

Computation and Language · Computer Science 2022-12-19 Ting Hua , Yen-Chang Hsu , Felicity Wang , Qian Lou , Yilin Shen , Hongxia Jin

We study the stochastic Riemannian gradient algorithm for matrix eigen-decomposition. The state-of-the-art stochastic Riemannian algorithm requires the learning rate to decay to zero and thus suffers from slow convergence and sub-optimal…

Machine Learning · Computer Science 2016-05-30 Zhiqiang Xu , Yiping Ke

We consider the problem of denoising with the help of prior information taken from a database of clean signals or images. Denoising with variational methods is very efficient if a regularizer well adapted to the nature of the data is…

Machine Learning · Computer Science 2023-10-06 Hui Shi , Yann Traonmilin , J-F Aujol

It is well known that it is challenging to train deep neural networks and recurrent neural networks for tasks that exhibit long term dependencies. The vanishing or exploding gradient problem is a well known issue associated with these…

Machine Learning · Computer Science 2017-10-13 Eugene Vorontsov , Chiheb Trabelsi , Samuel Kadoury , Chris Pal

We propose a Stein variational gradient descent method to concurrently sparsify, train, and provide uncertainty quantification of a complexly parameterized model such as a neural network. It employs a graph reconciliation and condensation…

Machine Learning · Computer Science 2024-12-24 Govinda Anantha Padmanabha , Cosmin Safta , Nikolaos Bouklas , Reese E. Jones

Spiking Neural Networks (SNNs) have been proposed as biologically plausible and energy-efficient alternatives to conventional Artificial Neural Networks (ANNs). However, the training of SNN usually relies on surrogate gradients due to the…

Neural and Evolutionary Computing · Computer Science 2026-05-11 Himanshu Udupi , Xiaocong Yang , ChengXiang Zhai

Particle-based approximate Bayesian inference approaches such as Stein Variational Gradient Descent (SVGD) combine the flexibility and convergence guarantees of sampling methods with the computational benefits of variational inference. In…

Machine Learning · Computer Science 2021-07-30 Lauro Langosco di Langosco , Vincent Fortuin , Heiko Strathmann

We present a simple yet novel parameterized form of linear mapping to achieves remarkable network compression performance: a pseudo SVD called Ternary SVD (TSVD). Unlike vanilla SVD, TSVD limits the $U$ and $V$ matrices in SVD to ternary…

Machine Learning · Computer Science 2023-08-16 Boyu Chen , Hanxuan Chen , Jiao He , Fengyu Sun , Shangling Jui

Recurrent neural networks (RNNs) are particularly well-suited for modeling long-term dependencies in sequential data, but are notoriously hard to train because the error backpropagated in time either vanishes or explodes at an exponential…

Machine Learning · Computer Science 2019-08-28 Anil Kag , Ziming Zhang , Venkatesh Saligrama

This paper presents a post-processing algorithm for training fair neural network regression models that satisfy statistical parity, utilizing an explainable singular value decomposition (SVD) of the weight matrix. We propose a linear…

Machine Learning · Computer Science 2025-04-07 Zhiqun Zuo , Ding Zhu , Mohammad Mahdi Khalili

Deep neural networks (NNs) encounter scalability limitations when confronted with a vast array of neurons, thereby constraining their achievable network depth. To address this challenge, we propose an integration of tensor networks (TN)…

Disordered Systems and Neural Networks · Physics 2024-08-20 Saeed S. Jahromi , Roman Orus

While Convolutional Neural Networks (CNNs) excel at learning complex latent-space representations, their over-parameterization can lead to overfitting and reduced performance, particularly with limited data. This, alongside their high…

Computer Vision and Pattern Recognition · Computer Science 2024-01-17 Manish Sharma , Jamison Heard , Eli Saber , Panos P. Markopoulos

Rank minimization can be converted into tractable surrogate problems, such as Nuclear Norm Minimization (NNM) and Weighted NNM (WNNM). The problems related to NNM, or WNNM, can be solved iteratively by applying a closed-form proximal…

Computer Vision and Pattern Recognition · Computer Science 2019-02-18 Tae-Hyun Oh , Yasuyuki Matsushita , Yu-Wing Tai , In So Kweon