English
Related papers

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

200 papers

Simplex gradients are an essential feature of many derivative free optimization algorithms, and can be employed, for example, as part of the process of defining a direction of search, or as part of a termination criterion. The calculation…

Optimization and Control · Mathematics 2018-07-26 Ian Coope , Rachael Tappenden

Backpropagation algorithm is indispensable for the training of feedforward neural networks. It requires propagating error gradients sequentially from the output layer all the way back to the input layer. The backward locking in…

Machine Learning · Computer Science 2018-07-24 Zhouyuan Huo , Bin Gu , Qian Yang , Heng Huang

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

Neural Ordinary Differential Equations (Neural ODEs) are the continuous analog of Residual Neural Networks (ResNets). We investigate whether the discrete dynamics defined by a ResNet are close to the continuous one of a Neural ODE. We first…

Machine Learning · Computer Science 2022-09-16 Michael E. Sander , Pierre Ablin , Gabriel Peyré

Numerical simulation of ordinary differential equations (ODEs) can be challenging when the system exhibits high accelerations and rapidly changing dynamics. Under these conditions the ODE solver often needs to take very small time steps in…

Numerical Analysis · Mathematics 2026-05-11 Andrew Tagg , Andrew Frandsen , Andrew Ning

The backpropagation algorithm remains the dominant and most successful method for training deep neural networks (DNNs). At the same time, training DNNs at scale comes at a significant computational cost and therefore a high carbon…

Machine Learning · Computer Science 2025-11-12 Sander Dalm , Joshua Offergeld , Nasir Ahmad , Marcel van Gerven

Backpropagation, the cornerstone of deep learning, is limited to computing gradients for continuous variables. This limitation poses challenges for problems involving discrete latent variables. To address this issue, we propose a novel…

Machine Learning · Computer Science 2023-10-17 Liyuan Liu , Chengyu Dong , Xiaodong Liu , Bin Yu , Jianfeng Gao

We propose to formulate MRI image reconstruction as an optimization problem and model the optimization trajectory as a dynamic process using ordinary differential equations (ODEs). We model the dynamics in ODE with a neural network and…

Image and Video Processing · Electrical Eng. & Systems 2020-09-16 Eric Z. Chen , Terrence Chen , Shanhui Sun

Does the use of auto-differentiation yield reasonable updates for deep neural networks (DNNs)? Specifically, when DNNs are designed to adhere to neural ODE architectures, can we trust the gradients provided by auto-differentiation? Through…

Machine Learning · Computer Science 2026-03-31 Yewei Xu , Shi Chen , Qin Li

Back-propagation is a popular machine learning algorithm that uses gradient descent in training neural networks for supervised learning, but can be very slow. A number of algorithms have been developed to speed up convergence and improve…

Neural and Evolutionary Computing · Computer Science 2020-09-29 Ho Ling Li

Embedding nonlinear dynamical systems into artificial neural networks is a powerful new formalism for machine learning. By parameterizing ordinary differential equations (ODEs) as neural network layers, these Neural ODEs are…

Machine Learning · Computer Science 2024-10-28 Mikko Lehtimäki , Lassi Paunonen , Marja-Leena Linne

Continuous-depth neural networks, such as Neural ODEs, have refashioned the understanding of residual neural networks in terms of non-linear vector-valued optimal control problems. The common solution is to use the adjoint sensitivity…

Machine Learning · Computer Science 2022-02-16 Andrew Corbett , Dmitry Kangin

Recurrent neural networks (RNNs) provide state-of-the-art performance in processing sequential data but are memory intensive to train, limiting the flexibility of RNN models which can be trained. Reversible RNNs---RNNs for which the…

Machine Learning · Computer Science 2018-10-26 Matthew MacKay , Paul Vicol , Jimmy Ba , Roger Grosse

Arguably the biggest challenge in applying neural networks is tuning the hyperparameters, in particular the learning rate. The sensitivity to the learning rate is due to the reliance on backpropagation to train the network. In this paper we…

Machine Learning · Statistics 2018-08-08 Francois Fagan , Garud Iyengar

Neural networks are achieving state of the art and sometimes super-human performance on learning tasks across a variety of domains. Whenever these problems require learning in a continual or sequential manner, however, neural networks…

Machine Learning · Computer Science 2019-10-17 Mehrdad Farajtabar , Navid Azizan , Alex Mott , Ang Li

Training deep neural networks on large-scale datasets requires significant hardware resources whose costs (even on cloud platforms) put them out of reach of smaller organizations, groups, and individuals. Backpropagation, the workhorse for…

Machine Learning · Computer Science 2020-09-22 Alexander Ororbia , Ankur Mali , Daniel Kifer , C. Lee Giles

Scientific problems require resolving multi-scale phenomena across different resolutions and learning solution operators in infinite-dimensional function spaces. Neural operators provide a powerful framework for this, using…

We propose a novel second-order optimization framework for training the emerging deep continuous-time models, specifically the Neural Ordinary Differential Equations (Neural ODEs). Since their training already involves expensive gradient…

Machine Learning · Computer Science 2021-11-09 Guan-Horng Liu , Tianrong Chen , Evangelos A. Theodorou

Neuroscientists fit morphologically and biophysically detailed neuron simulations to physiological data, often using evolutionary algorithms. However, such gradient-free approaches are computationally expensive, making convergence slow when…

Neurons and Cognition · Quantitative Biology 2024-07-23 Ilenna Simone Jones , Konrad Paul Kording

Embedding discrete solvers as differentiable layers has given modern deep learning architectures combinatorial expressivity and discrete reasoning capabilities. The derivative of these solvers is zero or undefined, therefore a meaningful…

Machine Learning · Computer Science 2024-12-16 Subham Sekhar Sahoo , Anselm Paulus , Marin Vlastelica , Vít Musil , Volodymyr Kuleshov , Georg Martius