English
Related papers

Related papers: Neural gradients are near-lognormal: improved quan…

200 papers

Pruning the weights of neural networks is an effective and widely-used technique for reducing model size and inference complexity. We develop and test a novel method based on compressed sensing which combines the pruning and training into a…

Computer Vision and Pattern Recognition · Computer Science 2021-04-08 Jonathan W. Siegel , Jianhong Chen , Pengchuan Zhang , Jinchao Xu

Pruning neural networks has regained interest in recent years as a means to compress state-of-the-art deep neural networks and enable their deployment on resource-constrained devices. In this paper, we propose a robust compressive learning…

Machine Learning · Computer Science 2020-06-05 George Retsinas , Athena Elafrou , Georgios Goumas , Petros Maragos

Quantization for deep neural networks have afforded models for edge devices that use less on-board memory and enable efficient low-power inference. In this paper, we present a comparison of model-parameter driven quantization approaches…

Computer Vision and Pattern Recognition · Computer Science 2019-10-14 Prateeth Nayak , David Zhang , Sek Chai

Accelerator memory and networking constraints have emerged as dominant bottlenecks when training large language models LLMs with billions of parameters. Existing low rank gradient estimators such as GaLoRE and FLORA compress gradients and…

Machine Learning · Computer Science 2025-05-27 Matan Haroush , Daniel Soudry

Quantization is an effective technique to reduce memory footprint, inference latency, and power consumption of deep learning models. However, existing quantization methods suffer from accuracy degradation compared to full-precision (FP)…

Machine Learning · Computer Science 2022-10-14 Zheng Wang , Juncheng B Li , Shuhui Qu , Florian Metze , Emma Strubell

Applying Differentially Private Stochastic Gradient Descent (DPSGD) to training modern, large-scale neural networks such as transformer-based models is a challenging task, as the magnitude of noise added to the gradients at each iteration…

Machine Learning · Computer Science 2022-07-07 Ryuichi Ito , Seng Pei Liew , Tsubasa Takahashi , Yuya Sasaki , Makoto Onizuka

Deep Neural Networks are generally trained using iterative gradient updates. Magnitudes of gradients are affected by many factors, including choice of activation functions and initialization. More importantly, gradient magnitudes can…

Machine Learning · Computer Science 2017-08-25 Sami Abu-El-Haija

In this paper, a gradient-free distributed algorithm is introduced to solve a set constrained optimization problem under a directed communication network. Specifically, at each time-step, the agents locally compute a so-called…

Optimization and Control · Mathematics 2021-09-06 Yipeng Pang , Guoqiang Hu

Recent years have witnessed significant success in Gradient Boosting Decision Trees (GBDT) for a wide range of machine learning applications. Generally, a consensus about GBDT's training algorithms is gradients and statistics are computed…

Machine Learning · Computer Science 2023-01-18 Yu Shi , Guolin Ke , Zhuoming Chen , Shuxin Zheng , Tie-Yan Liu

Linear layers in neural networks (NNs) trained by gradient descent can be expressed as a key-value memory system which stores all training datapoints and the initial weights, and produces outputs using unnormalised dot attention over the…

Machine Learning · Computer Science 2022-06-20 Kazuki Irie , Róbert Csordás , Jürgen Schmidhuber

Large language model (LLM) training and finetuning are often bottlenecked by limited GPU memory. While existing projection-based optimization methods address this by projecting gradients into a lower-dimensional subspace to reduce optimizer…

Machine Learning · Computer Science 2024-06-26 Aashiq Muhamed , Oscar Li , David Woodruff , Mona Diab , Virginia Smith

Distributed algorithms are often beset by the straggler effect, where the slowest compute nodes in the system dictate the overall running time. Coding-theoretic techniques have been recently proposed to mitigate stragglers via algorithmic…

Machine Learning · Statistics 2017-11-21 Zachary Charles , Dimitris Papailiopoulos , Jordan Ellenberg

Second-order training methods have better convergence properties than gradient descent but are rarely used in practice for large-scale training due to their computational overhead. This can be viewed as a hardware limitation (imposed by…

Machine Learning · Computer Science 2024-05-24 Kaelan Donatella , Samuel Duffield , Maxwell Aifer , Denis Melanson , Gavin Crooks , Patrick J. Coles

We present a post-training weight pruning method for deep neural networks that achieves accuracy levels tolerable for the production setting and that is sufficiently fast to be run on commodity hardware such as desktop CPUs or edge devices.…

Computer Vision and Pattern Recognition · Computer Science 2021-05-03 Ivan Lazarevich , Alexander Kozlov , Nikita Malinin

Large neural network models present a hefty communication challenge to distributed Stochastic Gradient Descent (SGD), with a communication complexity of O(n) per worker for a model of n parameters. Many sparsification and quantization…

Machine Learning · Computer Science 2020-06-17 Subhadeep Bhattacharya , Weikuan Yu , Fahim Tahmid Chowdhury

Stochastic gradient descent (SGD) is commonly used for optimization in large-scale machine learning problems. Langford et al. (2009) introduce a sparse online learning method to induce sparsity via truncated gradient. With high-dimensional…

Machine Learning · Statistics 2017-05-10 Yuting Ma , Tian Zheng

Obtaining versions of deep neural networks that are both highly-accurate and highly-sparse is one of the main challenges in the area of model compression, and several high-performance pruning techniques have been investigated by the…

Machine Learning · Computer Science 2023-09-11 Denis Kuznedelev , Eldar Kurtic , Eugenia Iofinova , Elias Frantar , Alexandra Peste , Dan Alistarh

Training Convolutional Neural Networks (CNNs) usually requires a large number of computational resources. In this paper, \textit{SparseTrain} is proposed to accelerate CNN training by fully exploiting the sparsity. It mainly involves three…

Computer Vision and Pattern Recognition · Computer Science 2020-07-28 Pengcheng Dai , Jianlei Yang , Xucheng Ye , Xingzhou Cheng , Junyu Luo , Linghao Song , Yiran Chen , Weisheng Zhao

Deep neural networks (DNNs) have been proven to be effective in solving many real-life problems, but its high computation cost prohibits those models from being deployed to edge devices. Pruning, as a method to introduce zeros to model…

Machine Learning · Computer Science 2021-12-22 Fei Sun , Minghai Qin , Tianyun Zhang , Xiaolong Ma , Haoran Li , Junwen Luo , Zihao Zhao , Yen-Kuang Chen , Yuan Xie

Deep learning has led to tremendous advancements in the field of Artificial Intelligence. One caveat however is the substantial amount of compute needed to train these deep learning models. Training a benchmark dataset like ImageNet on a…

Machine Learning · Computer Science 2018-10-30 Karanbir Chahal , Manraj Singh Grover , Kuntal Dey