English
Related papers

Related papers: Gradient Forward-Propagation for Large-Scale Tempo…

200 papers

Computational Fluid Dynamics (CFD) is used in the design and optimization of gas turbines and many other industrial/ scientific applications. However, the practical use is often limited by the high computational cost, and the accurate…

Fluid Dynamics · Physics 2023-11-29 Jan Hückelheim , Tadbhagya Kumar , Krishnan Raghavan , Pinaki Pal

Despite the notable success of deep neural networks (DNNs) in solving complex tasks, the training process still remains considerable challenges. A primary obstacle is the substantial time required for training, particularly as high…

Machine Learning · Computer Science 2025-09-09 Viet Hoang Pham , Hyo-Sung Ahn

Continuously adapting pre-trained models to local data on resource constrained edge devices is the $\emph{last mile}$ for model deployment. However, as models increase in size and depth, backpropagation requires a large amount of memory,…

Machine Learning · Computer Science 2024-11-07 Chen Feng , Shaojie Zhuo , Xiaopeng Zhang , Ramchalam Kinattinkara Ramakrishnan , Zhaocong Yuan , Andrew Zou Li

Sparse training is a natural idea to accelerate the training speed of deep neural networks and save the memory usage, especially since large modern neural networks are significantly over-parameterized. However, most of the existing methods…

Machine Learning · Computer Science 2021-11-11 Xiao Zhou , Weizhong Zhang , Zonghao Chen , Shizhe Diao , Tong Zhang

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

Exploiting sparsity enables hardware systems to run neural networks faster and more energy-efficiently. However, most prior sparsity-centric optimization techniques only accelerate the forward pass of neural networks and usually require an…

Machine Learning · Computer Science 2018-06-05 Maohua Zhu , Jason Clemons , Jeff Pool , Minsoo Rhu , Stephen W. Keckler , Yuan Xie

Fitting generative models to sequential data typically involves two recursive computations through time, one forward and one backward. The latter could be a computation of the loss gradient (as in backpropagation through time), or an…

Machine Learning · Computer Science 2023-10-23 Azwar Abdulsalam , Joseph G. Makin

Training neural networks with reinforcement learning (RL) typically relies on backpropagation (BP), necessitating storage of activations from the forward pass for subsequent backward updates. Furthermore, backpropagating error signals…

Machine Learning · Computer Science 2025-07-16 Daniel Tanneberg

Gradient-based learning in multi-layer neural networks displays a number of striking features. In particular, the decrease rate of empirical risk is non-monotone even after averaging over large batches. Long plateaus in which one observes…

Machine Learning · Computer Science 2025-03-25 Raphaël Berthier , Andrea Montanari , Kangjie Zhou

Temporal-difference (TD) learning is highly effective at controlling and evaluating an agent's long-term outcomes. Most approaches in this paradigm implement a semi-gradient update to boost the learning speed, which consists of ignoring the…

Machine Learning · Computer Science 2026-05-15 Théo Vincent , Kevin Gerhardt , Yogesh Tripathi , Habib Maraqten , Adam White , Martha White , Jan Peters , Carlo D'Eramo

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 presents a new method for pre-training neural networks that can decrease the total training time for a neural network while maintaining the final performance, which motivates its use on deep neural networks. By partitioning the…

Neural and Evolutionary Computing · Computer Science 2016-01-05 Conrado S. Miranda , Fernando J. Von Zuben

Recurrent neural networks are a successful neural architecture for many time-dependent problems, including time series analysis, forecasting, and modeling of dynamical systems. Training such networks with backpropagation through time is a…

Machine Learning · Computer Science 2025-01-30 Erik Lien Bolager , Ana Cukarska , Iryna Burak , Zahra Monfared , Felix Dietrich

Deep Neural Network (DNN) models are usually trained sequentially from one layer to another, which causes forward, backward and update locking's problems, leading to poor performance in terms of training time. The existing parallel…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-07-25 Samson B. Akintoye , Liangxiu Han , Huw Lloyd , Xin Zhang , Darren Dancey , Haoming Chen , Daoqiang Zhang

Recently, large-scale pre-trained vision-language models (e.g., CLIP), have garnered significant attention thanks to their powerful representative capabilities. This inspires researchers in transferring the knowledge from these large…

Computer Vision and Pattern Recognition · Computer Science 2025-06-13 Bin Wang , Wentong Li , Wenqian Wang , Mingliang Gao , Runmin Cong , Wei Zhang

We propose a scalable Forward-Forward (FF) algorithm that eliminates the need for backpropagation by training each layer separately. Unlike backpropagation, FF avoids backward gradients and can be more modular and memory efficient, making…

Machine Learning · Computer Science 2025-01-07 Andrii Krutsylo

End-to-end backpropagation requires storing activations throughout all layers, creating memory bottlenecks that limit model scalability. Existing block-wise training methods offer means to alleviate this problem, but they rely on ad-hoc…

Machine Learning · Computer Science 2026-02-19 Makoto Shing , Masanori Koyama , Takuya Akiba

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

In many sequential tasks, a model needs to remember relevant events from the distant past to make correct predictions. Unfortunately, a straightforward application of gradient based training requires intermediate computations to be stored…

Machine Learning · Computer Science 2023-08-14 Artyom Sorokin , Nazar Buzun , Leonid Pugachev , Mikhail Burtsev

Due to the substantial computational cost, training state-of-the-art deep neural networks for large-scale datasets often requires distributed training using multiple computation workers. However, by nature, workers need to frequently…

Machine Learning · Computer Science 2018-02-21 Yusuke Tsuzuku , Hiroto Imachi , Takuya Akiba