English
Related papers

Related papers: A Mini-Block Fisher Method for Deep Neural Network…

200 papers

Multi-output deep neural networks(MONs) contain multiple task branches, and these tasks usually share partial network filters that lead to the entanglement of different task inference routes. Due to the inconsistent optimization objectives,…

Computer Vision and Pattern Recognition · Computer Science 2025-12-22 Yi Sun , Xin Xu , Jian Li , Xiaochang Hu , Yifei Shi , Ling-Li Zeng

Recent advancements in large-scale pretrained models have significantly improved performance across a variety of tasks in natural language processing and computer vision. However, the extensive number of parameters in these models…

Machine Learning · Computer Science 2024-03-21 Jiang Hu , Quanzheng Li

Block Floating Point (BFP) can efficiently support quantization for Deep Neural Network (DNN) training by providing a wide dynamic range via a shared exponent across a group of values. In this paper, we propose a Fast First, Accurate Second…

Machine Learning · Computer Science 2021-11-01 Sai Qian Zhang , Bradley McDanel , H. T. Kung

Graph neural networks are recognized for their strong performance across various applications, with the backpropagation algorithm playing a central role in the development of most GNN models. However, despite its effectiveness, BP has…

Machine Learning · Computer Science 2024-11-06 Gongpei Zhao , Tao Wang , Congyan Lang , Yi Jin , Yidong Li , Haibin Ling

Supercomputer FCFS-based scheduling policies result in many transient idle nodes, a phenomenon that is only partially alleviated by backfill scheduling methods that promote small jobs to run before large jobs. Here we describe how to…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-06-24 Zhengchun Liu , Rajkumar Kettimuthu , Michael E. Papka , Ian Foster

A deep neural network is a hierarchical nonlinear model transforming input signals to output signals. Its input-output relation is considered to be stochastic, being described for a given input by a parameterized conditional probability…

Machine Learning · Computer Science 2018-08-23 Shun-ichi Amari , Ryo Karakida , Masafumi Oizumi

Mini-batch gradient descent based methods are the de facto algorithms for training neural network architectures today. We introduce a mini-batch selection strategy based on submodular function maximization. Our novel submodular formulation…

Machine Learning · Computer Science 2019-06-21 K J Joseph , Vamshi Teja R , Krishnakant Singh , Vineeth N Balasubramanian

Training deep neural networks (DNNs) with backpropagation (BP) achieves state-of-the-art accuracy but requires global error propagation and full parameterization, leading to substantial memory and computational overhead. Direct Feedback…

Machine Learning · Computer Science 2025-10-30 Arani Roy , Marco P. Apolinario , Shristi Das Biswas , Kaushik Roy

We propose a new per-layer adaptive step-size procedure for stochastic first-order optimization methods for minimizing empirical loss functions in deep learning, eliminating the need for the user to tune the learning rate (LR). The proposed…

Machine Learning · Computer Science 2023-07-07 Achraf Bahamou , Donald Goldfarb

Background: It is still an open research area to theoretically understand why Deep Neural Networks (DNNs)---equipped with many more parameters than training data and trained by (stochastic) gradient-based methods---often achieve remarkably…

Machine Learning · Computer Science 2018-11-30 Zhiqin John Xu

This work proposes a time-efficient Natural Gradient Descent method, called TENGraD, with linear convergence guarantees. Computing the inverse of the neural network's Fisher information matrix is expensive in NGD because the Fisher matrix…

Machine Learning · Computer Science 2022-03-04 Saeed Soori , Bugra Can , Baourun Mu , Mert Gürbüzbalaban , Maryam Mehri Dehnavi

First-order methods such as stochastic gradient descent (SGD) are currently the standard algorithm for training deep neural networks. Second-order methods, despite their better convergence rate, are rarely used in practice due to the…

Machine Learning · Computer Science 2019-09-26 Tianle Cai , Ruiqi Gao , Jikai Hou , Siyu Chen , Dong Wang , Di He , Zhihua Zhang , Liwei Wang

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

Modern GPUs are equipped with large amounts of high-bandwidth memory, enabling them to support mini-batch sizes of up to tens of thousands of training samples. However, most existing optimizers struggle to perform effectively at such a…

Machine Learning · Computer Science 2026-02-10 Yishun Lu , Wesley Armour

Pipeline parallelism enables efficient training of Large Language Models (LLMs) on large-scale distributed accelerator clusters. Yet, pipeline bubbles during startup and tear-down reduce the utilization of accelerators. Although efficient…

Machine Learning · Computer Science 2023-05-16 Kazuki Osawa , Shigang Li , Torsten Hoefler

Distributed synchronous stochastic gradient descent has been widely used to train deep neural networks (DNNs) on computer clusters. With the increase of computational power, network communications generally limit the system scalability.…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-01-19 Shaohuai Shi , Xiaowen Chu , Bo Li

We propose an efficient method for approximating natural gradient descent in neural networks which we call Kronecker-Factored Approximate Curvature (K-FAC). K-FAC is based on an efficiently invertible approximation of a neural network's…

Machine Learning · Computer Science 2020-06-09 James Martens , Roger Grosse

It has been believed that stochastic feedforward neural networks (SFNNs) have several advantages beyond deterministic deep neural networks (DNNs): they have more expressive power allowing multi-modal mappings and regularize better due to…

Machine Learning · Computer Science 2017-04-12 Kimin Lee , Jaehyung Kim , Song Chong , Jinwoo Shin

Standard methods for differentially private training of deep neural networks replace back-propagated mini-batch gradients with biased and noisy approximations to the gradient. These modifications to training often result in a…

Machine Learning · Computer Science 2020-10-09 Jaewoo Lee , Daniel Kifer

Deep neural networks are typically represented by a much larger number of parameters than shallow models, making them prohibitive for small footprint devices. Recent research shows that there is considerable redundancy in the parameter…

Machine Learning · Computer Science 2016-05-17 Ming Tu , Visar Berisha , Yu Cao , Jae-sun Seo