English
Related papers

Related papers: Unit-Consistent (UC) Adjoint for GSD and Backprop …

200 papers

The great success neural networks have achieved is inseparable from the application of gradient-descent (GD) algorithms. Based on GD, many variant algorithms have emerged to improve the GD optimization process. The gradient for…

Machine Learning · Computer Science 2023-05-29 Zefan Li , Bingbing Ni , Teng Li , WenJun Zhang , Wen Gao

This paper studies the approximation property of ReLU neural networks (NNs) to piecewise constant functions with unknown interfaces in bounded regions in $\mathbb{R}^d$. Under the assumption that the discontinuity interface $\Gamma$ may be…

Functional Analysis · Mathematics 2024-10-23 Zhiqiang Cai , Junpyo Choi , Min Liu

This work focuses on the decentralized deep learning optimization framework. We propose Adjacent Leader Decentralized Gradient Descent (AL-DSGD), for improving final model performance, accelerating convergence, and reducing the…

Machine Learning · Computer Science 2024-08-21 Haoze He , Jing Wang , Anna Choromanska

In learning with recurrent or very deep feed-forward networks, employing unitary matrices in each layer can be very effective at maintaining long-range stability. However, restricting network parameters to be unitary typically comes at the…

Machine Learning · Computer Science 2022-10-17 Bobak Kiani , Randall Balestriero , Yann LeCun , Seth Lloyd

A scaled conjugate gradient method that accelerates existing adaptive methods utilizing stochastic gradients is proposed for solving nonconvex optimization problems with deep neural networks. It is shown theoretically that, whether with…

Machine Learning · Computer Science 2024-12-17 Naoki Sato , Koshiro Izumi , Hideaki Iiduka

The ever-growing deep learning technologies are making revolutionary changes for modern life. However, conventional computing architectures are designed to process sequential and digital programs, being extremely burdened with performing…

Emerging Technologies · Computer Science 2022-12-21 Yuyao Huang , Tingzhao Fu , Honghao Huang , Sigang Yang , Hongwei Chen

Stochastic gradient descent (SGD) is a widely adopted iterative method for optimizing differentiable objective functions. In this paper, we propose and discuss a novel approach to scale up SGD in applications involving non-convex functions…

Machine Learning · Statistics 2022-10-07 Saad Mohamad , Hamad Alamri , Abdelhamid Bouchachia

Gradient Descent (GD) and its variants are the primary tool for enabling efficient training of recurrent dynamical systems such as Recurrent Neural Networks (RNNs), Neural ODEs and Gated Recurrent units (GRUs). The dynamics that are formed…

Machine Learning · Computer Science 2025-07-10 James Hazelden , Laura Driscoll , Eli Shlizerman , Eric Shea-Brown

Momentum plays a crucial role in stochastic gradient-based optimization algorithms for accelerating or improving training deep neural networks (DNNs). In deep learning practice, the momentum is usually weighted by a well-calibrated…

Machine Learning · Computer Science 2020-12-04 Bao Wang , Qiang Ye

Neural differential equations may be trained by backpropagating gradients via the adjoint method, which is another differential equation typically solved using an adaptive-step-size numerical differential equation solver. A proposed step is…

Machine Learning · Computer Science 2021-05-11 Patrick Kidger , Ricky T. Q. Chen , Terry Lyons

A number of results have recently demonstrated the benefits of incorporating various constraints when training deep architectures in vision and machine learning. The advantages range from guarantees for statistical generalization to better…

Machine Learning · Computer Science 2019-05-27 Sathya N. Ravi , Tuan Dinh , Vishnu Lokhande , Vikas Singh

Deep neural networks have achieved great success both in computer vision and natural language processing tasks. However, mostly state-of-art methods highly rely on external training or computing to improve the performance. To alleviate the…

Machine Learning · Computer Science 2020-09-25 Ming Yan , Xueli Xiao , Joey Tianyi Zhou , Yi Pan

The ResNet architecture has been widely adopted in deep learning due to its significant boost to performance through the use of simple skip connections, yet the underlying mechanisms leading to its success remain largely unknown. In this…

Machine Learning · Computer Science 2024-01-18 Jianing Li , Vardan Papyan

Graph Convolutional Networks (GCNs) have been widely demonstrated their powerful ability in graph data representation and learning. Existing graph convolution layers are mainly designed based on graph signal processing and transform aspect…

Computer Vision and Pattern Recognition · Computer Science 2022-04-27 Ziyan Zhang , Bo Jiang , Bin Luo

This paper develops a randomized approach for incrementally building deep neural networks, where a supervisory mechanism is proposed to constrain the random assignment of the weights and biases, and all the hidden layers have direct links…

Machine Learning · Computer Science 2018-03-19 Dianhui Wang , Ming Li

Backpropagation is the default learning rule for artificial neural networks and is often treated as the settled approach whenever differentiability is available. In this work, we revisit this convention through a theoretical lens of sample…

Machine Learning · Statistics 2026-05-28 Yibo Jacky Zhang , Zeyu Tang , Sanmi Koyejo

How can local-search methods such as stochastic gradient descent (SGD) avoid bad local minima in training multi-layer neural networks? Why can they fit random labels even given non-convex and non-smooth architectures? Most existing theory…

Machine Learning · Computer Science 2019-05-28 Zeyuan Allen-Zhu , Yuanzhi Li , Zhao Song

A recent paper by Boughammoura (2023) describes the back-propagation algorithm in terms of an alternative formulation called the F-adjoint method. In particular, by the F-adjoint algorithm the computation of the loss gradient, with respect…

Machine Learning · Computer Science 2024-07-17 Ahmed Boughammoura

We study approximation and statistical learning properties of deep ReLU networks under structural assumptions that mitigate the curse of dimensionality. We prove minimax-optimal uniform approximation rates for $s$-H\"older smooth functions…

Statistics Theory · Mathematics 2026-02-06 Thomas Nagler , Sophie Langer

Recurrent Neural Networks (RNNs) are designed to handle sequential data but suffer from vanishing or exploding gradients. Recent work on Unitary Recurrent Neural Networks (uRNNs) have been used to address this issue and in some cases,…

Machine Learning · Statistics 2018-06-20 Kyle Helfrich , Devin Willmott , Qiang Ye