English
Related papers

Related papers: Efficient, Accurate and Stable Gradients for Neura…

200 papers

The vast majority of successful deep neural networks are trained using variants of stochastic gradient descent (SGD) algorithms. Recent attempts to improve SGD can be broadly categorized into two approaches: (1) adaptive learning rate…

Machine Learning · Computer Science 2019-12-04 Michael R. Zhang , James Lucas , Geoffrey Hinton , Jimmy Ba

The performance of gradient-based optimization methods, such as standard gradient descent (GD), greatly depends on the choice of learning rate. However, it can require a non-trivial amount of user tuning effort to select an appropriate…

Machine Learning · Computer Science 2025-10-14 Nikola Surjanovic , Alexandre Bouchard-Côté , Trevor Campbell

Two-step predictor/corrector methods are provided to solve three classes of problems that present themselves as systems of ordinary differential equations (ODEs). In the first class, velocities are given from which displacements are to be…

Numerical Analysis · Computer Science 2017-07-10 Alan D. Freed

We study the inverse problem of radiative transfer equation (RTE) using stochastic gradient descent method (SGD) in this paper. Mathematically, optical tomography amounts to recovering the optical parameters in RTE using the…

Optimization and Control · Mathematics 2018-07-04 Ke Chen , Qin Li , Jian-Guo Liu

Training deep neural networks (DNNs) efficiently is a challenge due to the associated highly nonconvex optimization. The backpropagation (backprop) algorithm has long been the most widely used algorithm for gradient computation of…

Machine Learning · Statistics 2018-03-28 Tim Tsz-Kit Lau , Jinshan Zeng , Baoyuan Wu , Yuan Yao

Residual networks (ResNets) are a deep learning architecture that substantially improved the state of the art performance in certain supervised learning tasks. Since then, they have received continuously growing attention. ResNets have a…

Machine Learning · Computer Science 2020-03-02 Johannes Müller

We propose proximal backpropagation (ProxProp) as a novel algorithm that takes implicit instead of explicit gradient steps to update the network parameters during neural network training. Our algorithm is motivated by the step size…

Machine Learning · Computer Science 2018-02-21 Thomas Frerix , Thomas Möllenhoff , Michael Moeller , Daniel Cremers

Neural networks can be used to learn the solution of partial differential equations (PDEs) on arbitrary domains without requiring a computational mesh. Common approaches integrate differential operators in training neural networks using a…

Machine Learning · Computer Science 2022-07-07 Shamsulhaq Basir , Inanc Senocak

Regressing rotations on SO(3) manifold using deep neural networks is an important yet unsolved problem. The gap between the Euclidean network output space and the non-Euclidean SO(3) manifold imposes a severe challenge for neural network…

Computer Vision and Pattern Recognition · Computer Science 2022-03-31 Jiayi Chen , Yingda Yin , Tolga Birdal , Baoquan Chen , Leonidas Guibas , He Wang

Neural networks have been able to achieve groundbreaking accuracy at tasks conventionally considered only doable by humans. Using stochastic gradient descent, optimization in many dimensions is made possible, albeit at a relatively high…

Machine Learning · Computer Science 2017-07-17 Hirsh R. Agarwal , Andrew Huang

Neural ODEs demonstrate strong performance in generative and time-series modelling. However, training them via the adjoint method is slow compared to discrete models due to the requirement of numerically solving ODEs. To speed neural ODEs…

Machine Learning · Computer Science 2023-08-22 Alexander Norcliffe , Marc Peter Deisenroth

Training a neural network using backpropagation algorithm requires passing error gradients sequentially through the network. The backward locking prevents us from updating network layers in parallel and fully leveraging the computing…

Machine Learning · Computer Science 2019-05-30 Zhouyuan Huo , Bin Gu , Heng Huang

This paper explores the application of the parameter-shift rule (PSR) for computing gradients in unitary optical neural networks (UONNs). While backpropagation has been fundamental to training conventional neural networks, its…

Emerging Technologies · Computer Science 2025-06-16 Jinzhe Jiang , Yaqian Zhao , Xin Zhang , Chen Li , Yunlong Yu , Hailing Liu

We present an approach to backpropagating through minimal problem solvers in end-to-end neural network training. Traditional methods relying on manually constructed formulas, finite differences, and autograd are laborious, approximate, and…

Computer Vision and Pattern Recognition · Computer Science 2024-06-11 Diana Sungatullina , Tomas Pajdla

We present an adaptive algorithm for effectively solving rough differential equations (RDEs) using the log-ODE method. The algorithm is based on an error representation formula that accurately describes the contribution of local errors to…

Numerical Analysis · Mathematics 2023-07-25 Christian Bayer , Simon Breneis , Terry Lyons

Residual connections are central to modern deep neural networks, enabling stable optimization and efficient information flow across depth. In this work, we propose SCORE (Skip-Connection ODE Recurrent Embedding), a discrete recurrent…

Machine Learning · Computer Science 2026-03-12 Guillaume Godin

We introduce a general method for improving the convergence rate of gradient-based optimizers that is easy to implement and works well in practice. We demonstrate the effectiveness of the method in a range of optimization problems by…

Machine Learning · Computer Science 2018-08-23 Atilim Gunes Baydin , Robert Cornish , David Martinez Rubio , Mark Schmidt , Frank Wood

Training Convolutional Neural Networks (CNN) is a resource intensive task that requires specialized hardware for efficient computation. One of the most limiting bottleneck of CNN training is the memory cost associated with storing the…

Computer Vision and Pattern Recognition · Computer Science 2019-10-25 Tristan Hascoet , Quentin Febvre , Yasuo Ariki , Tetsuya Takiguchi

Memory-efficient optimization methods have recently gained increasing attention for scaling full-parameter training of large language models under the GPU-memory bottleneck. Existing approaches either lack clear convergence guarantees, or…

Machine Learning · Computer Science 2026-03-11 Hui Yang , Tao Ren , Jinyang Jiang , Wan Tian , Yijie Peng

Fine-tuning pretrained models has become a standard approach to adapting pretrained knowledge to improve the accuracy on new sparse, imbalance datasets. However, issues arise when optimization falls into a collapsed state, where the model…

Machine Learning · Computer Science 2026-05-01 Nghia Bui , Lijing Wang