English
Related papers

Related papers: First Demonstration of Second-order Training of De…

200 papers

Running out of GPU memory has become a main bottleneck for large-scale DNN training. How to reduce the memory footprint during training has received intensive research attention. We find that previous gradient accumulation reduces…

Machine Learning · Computer Science 2023-06-01 Yijia Zhang , Yibo Han , Shijie Cao , Guohao Dai , Youshan Miao , Ting Cao , Fan Yang , Ningyi Xu

While the superior performance of second-order optimization methods such as Newton's method is well known, they are hardly used in practice for deep learning because neither assembling the Hessian matrix nor calculating its inverse is…

Machine Learning · Computer Science 2020-09-16 Siyuan Shen , Tianjia Shao , Kun Zhou , Chenfanfu Jiang , Feng Luo , Yin Yang

Training deep neural networks (DNNs) used in modern machine learning is computationally expensive. Machine learning scientists, therefore, rely on stochastic first-order methods for training, coupled with significant hand-tuning, to obtain…

Machine Learning · Computer Science 2023-07-24 Eric Silk , Swarnita Chakraborty , Nairanjana Dasgupta , Anand D. Sarwate , Andrew Lumsdaine , Tony Chiang

In several recently proposed stochastic optimization methods (e.g. RMSProp, Adam, Adadelta), parameter updates are scaled by the inverse square roots of exponential moving averages of squared past gradients. Maintaining these per-parameter…

Machine Learning · Computer Science 2018-04-13 Noam Shazeer , Mitchell Stern

This work proposes Alada, an adaptive momentum method for stochastic optimization over large-scale matrices. Alada employs a rank-one factorization approach to estimate the second moment of gradients, where factors are updated alternatively…

Machine Learning · Computer Science 2025-12-16 Xiaoyu He , Yu Cai , Jin Jia , Canxi Huang , Wenqing Chen , Zibin Zheng

This paper presents an implementation of multilayer feed forward neural networks (NN) to optimize CMOS analog circuits. For modeling and design recently neural network computational modules have got acceptance as an unorthodox and useful…

Neural and Evolutionary Computing · Computer Science 2012-12-13 Mriganka Chakraborty

Operations typically used in machine learning al-gorithms (e.g. adds and soft max) can be implemented bycompact analog circuits. Analog Application-Specific Integrated Circuit (ASIC) designs that implement these algorithms using techniques…

Neural and Evolutionary Computing · Computer Science 2021-06-24 Shih-Chii Liu , John Paul Strachan , Arindam Basu

Coordinate networks are widely used in computer vision due to their ability to represent signals as compressed, continuous entities. However, training these networks with first-order optimizers can be slow, hindering their use in real-time…

Computer Vision and Pattern Recognition · Computer Science 2023-05-16 Hemanth Saratchandran , Shin-Fang Chng , Sameera Ramasinghe , Lachlan MacDonald , Simon Lucey

Adaptive gradient methods, which adopt historical gradient information to automatically adjust the learning rate, despite the nice property of fast convergence, have been observed to generalize worse than stochastic gradient descent (SGD)…

Machine Learning · Computer Science 2020-06-24 Jinghui Chen , Dongruo Zhou , Yiqi Tang , Ziyan Yang , Yuan Cao , Quanquan Gu

The on-chip implementation of learning algorithms would speed-up the training of neural networks in crossbar arrays. The circuit level design and implementation of backpropagation algorithm using gradient descent operation for neural…

Emerging Technologies · Computer Science 2018-09-03 Olga Krestinskaya , Khaled Nabil Salama , Alex Pappachen James

Gradient descent based optimization methods are the methods of choice to train deep neural networks in machine learning. Beyond the standard gradient descent method, also suitable modified variants of standard gradient descent involving…

Optimization and Control · Mathematics 2025-04-29 Steffen Dereich , Arnulf Jentzen , Adrian Riekert

The stochastic gradient descent (SGD) algorithm has achieved remarkable success in training deep learning models. However, it has several limitations, including susceptibility to vanishing gradients, sensitivity to input data, and a lack of…

Machine Learning · Computer Science 2025-03-14 Chengcheng Yan , Jiawei Xu , Qingsong Wang , Zheng Peng

This work demonstrates a hardware-efficient support vector machine (SVM) training algorithm via the alternative direction method of multipliers (ADMM) optimizer. Low-rank approximation is exploited to reduce the dimension of the kernel…

Signal Processing · Electrical Eng. & Systems 2019-07-24 Shuo-An Huang , Chia-Hsiang Yang

Edge computing is a promising solution for handling high-dimensional, multispectral analog data from sensors and IoT devices for applications such as autonomous drones. However, edge devices' limited storage and computing resources make it…

Machine Learning · Computer Science 2023-09-21 Nastaran Darabi , Amit R. Trivedi

Second-order optimizers hold intriguing potential for deep learning, but suffer from increased cost and sensitivity to the non-convexity of the loss surface as compared to gradient-based approaches. We introduce a coordinate descent method…

Machine Learning · Computer Science 2020-06-19 Ravi G. Patel , Nathaniel A. Trask , Mamikon A. Gulian , Eric C. Cyr

Alternating Direction Method of Multipliers (ADMM) has been used successfully in many conventional machine learning applications and is considered to be a useful alternative to Stochastic Gradient Descent (SGD) as a deep learning optimizer.…

Optimization and Control · Mathematics 2021-07-07 Junxiang Wang , Fuxun Yu , Xiang Chen , Liang Zhao

In this paper, we present CT-AGD (Curvature-Tuned Accelerated Gradient Descent), an optimization method for non-convex optimization problems in deep learning training tasks. CT-AGD is a general boosting procedure that accelerates…

Machine Learning · Computer Science 2026-05-18 Manuel Graca , L. Miguel Silveira , Arlindo Oliveira , Frank Liu

Analog In-memory Computing (IMC) has demonstrated energy-efficient and low latency implementation of convolution and fully-connected layers in deep neural networks (DNN) by using physics for computing in parallel resistive memory arrays.…

Sharpness aware minimization (SAM) optimizer has been extensively explored as it can generalize better for training deep neural networks via introducing extra perturbation steps to flatten the landscape of deep learning models. Integrating…

Machine Learning · Computer Science 2023-03-02 Hao Sun , Li Shen , Qihuang Zhong , Liang Ding , Shixiang Chen , Jingwei Sun , Jing Li , Guangzhong Sun , Dacheng Tao

In recent years, spiking neural networks (SNNs) have gained momentum due to their high potential in time-series processing combined with minimal energy consumption. However, they still lack a dedicated and efficient training algorithm. The…

Machine Learning · Computer Science 2026-01-21 Giovanni Perin , Cesare Bidini , Riccardo Mazzieri , Michele Rossi