English
Related papers

Related papers: DropIT: Dropping Intermediate Tensors for Memory-E…

200 papers

Sparse tensors appear frequently in distributed deep learning, either as a direct artifact of the deep neural network's gradients, or as a result of an explicit sparsification process. Existing communication primitives are agnostic to the…

Machine Learning · Computer Science 2021-02-08 Kelly Kostopoulou , Hang Xu , Aritra Dutta , Xin Li , Alexandros Ntoulas , Panos Kalnis

Training high-quality deep models necessitates vast amounts of data, resulting in overwhelming computational and memory demands. Recently, data pruning, distillation, and coreset selection have been developed to streamline data volume by…

Machine Learning · Computer Science 2024-10-18 Guibin Zhang , Haonan Dong , Yuchen Zhang , Zhixun Li , Dingshuo Chen , Kai Wang , Tianlong Chen , Yuxuan Liang , Dawei Cheng , Kun Wang

Graph Neural Networks (GNNs) show strong promise for circuit analysis, but scaling to modern large-scale circuit graphs is limited by GPU memory and training cost, especially for deep models. We revisit deep GNNs for circuit graphs and show…

Machine Learning · Computer Science 2026-03-31 Yuebo Luo , Shiyang Li , Yifei Feng , Vishal Kancharla , Shaoyi Huang , Caiwen Ding

Deep neural networks have made significant progress in the field of computer vision. Recent studies have shown that depth, width and shortcut connections of neural network architectures play a crucial role in their performance. One of the…

Computer Vision and Pattern Recognition · Computer Science 2021-12-30 Rui-Yang Ju , Ting-Yu Lin , Jen-Shiun Chiang

Dynamic DNN optimization techniques such as layer-skipping offer increased adaptability and efficiency gains but can lead to i) a larger memory footprint as in decision gates, ii) increased training complexity (e.g., with non-differentiable…

Machine Learning · Computer Science 2025-05-26 Guilherme Korol , Antonio Carlos Schneider Beck , Jeronimo Castrillon

The backpropagation algorithm remains the dominant and most successful method for training deep neural networks (DNNs). At the same time, training DNNs at scale comes at a significant computational cost and therefore a high carbon…

Machine Learning · Computer Science 2025-11-12 Sander Dalm , Joshua Offergeld , Nasir Ahmad , Marcel van Gerven

Memory optimization for deep neural network (DNN) inference gains high relevance with the emergence of TinyML, which refers to the deployment of DNN inference tasks on tiny, low-power microcontrollers. Applications such as audio keyword…

Machine Learning · Computer Science 2023-04-03 Rafael Stahl , Daniel Mueller-Gritschneder , Ulf Schlichtmann

Large-scale machine learning models are often trained by parallel stochastic gradient descent algorithms. However, the communication cost of gradient aggregation and model synchronization between the master and worker nodes becomes the…

Machine Learning · Computer Science 2020-07-03 Xiaorui Liu , Yao Li , Jiliang Tang , Ming Yan

Deep neural networks have dramatically achieved great success on a variety of challenging tasks. However, most successful DNNs have an extremely complex structure, leading to extensive research on model compression.As a significant area of…

Machine Learning · Computer Science 2020-04-13 Haipeng Jia , Xueshuang Xiang , Da Fan , Meiyu Huang , Changhao Sun , Yang He

Modern Deep Neural Networks (DNNs) require significant memory to store weight, activations, and other intermediate tensors during training. Hence, many models do not fit one GPU device or can be trained using only a small per-GPU batch…

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

The acceleration of pruned Deep Neural Networks (DNNs) on edge devices such as Microcontrollers (MCUs) is a challenging task, given the tight area- and power-constraints of these devices. In this work, we propose a three-fold contribution…

Machine Learning · Computer Science 2025-03-20 Francesco Daghero , Daniele Jahier Pagliari , Francesco Conti , Luca Benini , Massimo Poncino , Alessio Burrello

We introduce a DNN training technique that learns only a fraction of the full parameter set without incurring an accuracy penalty. To do this, our algorithm constrains the total number of weights updated during backpropagation to those with…

Machine Learning · Computer Science 2019-11-26 Maximilian Golub , Guy Lemieux , Mieszko Lis

Deep neural networks have become ubiquitous for applications related to visual recognition and language understanding tasks. However, it is often prohibitive to use typical neural networks on devices like mobile phones or smart watches…

Machine Learning · Computer Science 2017-08-10 Sujith Ravi

Deep neural networks (DNNs) often have to be compressed, via pruning and/or quantization, before they can be deployed in practical settings. In this work we propose a new compression-aware minimizer dubbed CrAM that modifies the…

Machine Learning · Computer Science 2023-05-05 Alexandra Peste , Adrian Vladu , Eldar Kurtic , Christoph H. Lampert , Dan Alistarh

Background: Distributed training is essential for large scale training of deep neural networks (DNNs). The dominant methods for large scale DNN training are synchronous (e.g. All-Reduce), but these require waiting for all workers in each…

Machine Learning · Computer Science 2023-09-26 Niv Giladi , Shahar Gottlieb , Moran Shkolnik , Asaf Karnieli , Ron Banner , Elad Hoffer , Kfir Yehuda Levy , Daniel Soudry

The resource requirements of deep neural networks (DNNs) pose significant challenges to their deployment on edge devices. Common approaches to address this issue are pruning and mixed-precision quantization, which lead to latency and memory…

To enable learning on edge devices with fast convergence and low memory, we present a novel backpropagation-free optimization algorithm dubbed Target Projection Stochastic Gradient Descent (tpSGD). tpSGD generalizes direct random target…

Machine Learning · Computer Science 2022-09-19 Michael Lomnitz , Zachary Daniels , David Zhang , Michael Piacentino

Fine-tuning provides an effective means to specialize pre-trained models for various downstream tasks. However, fine-tuning often incurs high memory overhead, especially for large transformer-based models, such as LLMs. While existing…

Computation and Language · Computer Science 2025-02-03 Antoine Simoulin , Namyong Park , Xiaoyi Liu , Grey Yang

Gradient descent can be surprisingly good at optimizing deep neural networks without overfitting and without explicit regularization. We find that the discrete steps of gradient descent implicitly regularize models by penalizing gradient…

Machine Learning · Computer Science 2022-07-20 David G. T. Barrett , Benoit Dherin
‹ Prev 1 8 9 10 Next ›