English
Related papers

Related papers: BPPSA: Scaling Back-propagation by Parallel Scan A…

200 papers

As neural networks become more integrated into the systems that we depend on for transportation, medicine, and security, it becomes increasingly important that we develop methods to analyze their behavior to ensure that they are safe to use…

Systems and Control · Electrical Eng. & Systems 2022-10-17 Nicholas Rober , Michael Everett , Songan Zhang , Jonathan P. How

We propose a memory efficient method, named Stochastic Backpropagation (SBP), for training deep neural networks on videos. It is based on the finding that gradients from incomplete execution for backpropagation can still effectively train…

Computer Vision and Pattern Recognition · Computer Science 2022-04-01 Feng Cheng , Mingze Xu , Yuanjun Xiong , Hao Chen , Xinyu Li , Wei Li , Wei Xia

Truncated Backpropagation Through Time (truncated BPTT) is a widespread method for learning recurrent computational graphs. Truncated BPTT keeps the computational benefits of Backpropagation Through Time (BPTT) while relieving the need for…

Neural and Evolutionary Computing · Computer Science 2017-05-24 Corentin Tallec , Yann Ollivier

We introduce the "NoBackTrack" algorithm to train the parameters of dynamical systems such as recurrent neural networks. This algorithm works in an online, memoryless setting, thus requiring no backpropagation through time, and is scalable,…

Neural and Evolutionary Computing · Computer Science 2015-11-24 Yann Ollivier , Corentin Tallec , Guillaume Charpiat

Most machine learning and deep neural network algorithms rely on certain iterative algorithms to optimise their utility/cost functions, e.g. Stochastic Gradient Descent. In distributed learning, the networked nodes have to work…

Distributed, Parallel, and Cluster Computing · Computer Science 2017-10-06 Liang Wang , Ben Catterall , Richard Mortier

Although deep neural networks (DNN) are able to scale with direct advances in computational power (e.g., memory and processing speed), they are not well suited to exploit the recent trends for parallel architectures. In particular, gradient…

Machine Learning · Computer Science 2016-05-24 Andrew J. R. Simpson

Topic modeling is a very powerful technique in data analysis and data mining but it is generally slow. Many parallelization approaches have been proposed to speed up the learning process. However, they are usually not very efficient because…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-02-24 Hung Nghiep Tran , Atsuhiro Takasu

As neural network algorithms show high performance in many applications, their efficient inference on mobile and embedded systems are of great interests. When a single stream recurrent neural network (RNN) is executed for a personal user in…

Distributed, Parallel, and Cluster Computing · Computer Science 2018-04-02 Wonyong Sung , Jinhwan Park

During inference, Recurrent Neural Networks (RNNs) scale constant in both FLOPs and GPU memory with increasing context length, as they compress all prior tokens into a fixed-size memory. In contrast, transformers scale linearly in FLOPs…

Machine Learning · Computer Science 2025-05-26 Francois Chaubard , Mykel Kochenderfer

While effective, the backpropagation (BP) algorithm exhibits limitations in terms of biological plausibility, computational cost, and suitability for online learning. As a result, there has been a growing interest in developing alternative…

Neural and Evolutionary Computing · Computer Science 2023-08-07 Yanis Bahroun , Shagesh Sridharan , Atithi Acharya , Dmitri B. Chklovskii , Anirvan M. Sengupta

The spiking neural network (SNN) mimics the information processing operation in the human brain, represents and transmits information in spike trains containing wealthy spatial and temporal information, and shows superior performance on…

Neural and Evolutionary Computing · Computer Science 2021-10-25 Guobin Shen , Dongcheng Zhao , Yi Zeng

Spiking Neural Networks (SNNs) are promising energy-efficient models for neuromorphic computing. For training the non-differentiable SNN models, the backpropagation through time (BPTT) with surrogate gradients (SG) method has achieved high…

Neural and Evolutionary Computing · Computer Science 2023-08-08 Qingyan Meng , Mingqing Xiao , Shen Yan , Yisen Wang , Zhouchen Lin , Zhi-Quan Luo

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

Dramatic increases in the capabilities of neural network models in recent years are driven by scaling model size, training data, and corresponding computational resources. To develop the exceedingly large networks required in modern…

Machine Learning · Computer Science 2025-04-15 Jared Fernandez , Luca Wehrstedt , Leonid Shamis , Mostafa Elhoushi , Kalyan Saladi , Yonatan Bisk , Emma Strubell , Jacob Kahn

The way how recurrently connected networks of spiking neurons in the brain acquire powerful information processing capabilities through learning has remained a mystery. This lack of understanding is linked to a lack of learning algorithms…

Neural and Evolutionary Computing · Computer Science 2019-02-22 Guillaume Bellec , Franz Scherr , Elias Hajek , Darjan Salaj , Robert Legenstein , Wolfgang Maass

Training deep learning networks involves continuous weight updates across the various layers of the deep network while using a backpropagation algorithm (BP). This results in expensive computation overheads during training. Consequently,…

Machine Learning · Computer Science 2021-02-23 D. Dang , S. V. R. Chittamuru , S. Pasricha , R. Mahapatra , D. Sahoo

Pre-training large neural networks at scale imposes heavy memory demands on accelerators and often requires costly communication. We introduce Subnetwork Data Parallelism (SDP), a distributed training framework that partitions a model into…

Machine Learning · Computer Science 2025-10-06 Vaibhav Singh , Zafir Khalid , Edouard Oyallon , Eugene Belilovsky

It is commonly believed that scaling language models should commit a significant space or time cost, by increasing the parameters (parameter scaling) or output tokens (inference-time scaling). We introduce the third and more…

Machine Learning · Computer Science 2025-05-16 Mouxiang Chen , Binyuan Hui , Zeyu Cui , Jiaxi Yang , Dayiheng Liu , Jianling Sun , Junyang Lin , Zhongxin Liu

Large language models (LLMs) have achieved significant success across various domains. However, training these LLMs typically involves substantial memory and computational costs during both forward and backward propagation. While…

Machine Learning · Computer Science 2025-03-03 Sunghyeon Woo , Baeseong Park , Byeongwook Kim , Minjung Jo , Se Jung Kwon , Dongsuk Jeon , Dongsoo Lee

The bulk synchronous parallel (BSP) is a celebrated synchronization model for general-purpose parallel computing that has successfully been employed for distributed training of machine learning models. A prevalent shortcoming of the BSP is…

Machine Learning · Computer Science 2020-01-07 Xing Zhao , Manos Papagelis , Aijun An , Bao Xin Chen , Junfeng Liu , Yonggang Hu