English
Related papers

Related papers: Memory Optimization for Deep Networks

200 papers

This study identifies and proposes techniques to alleviate two key bottlenecks to executing deep neural networks in trusted execution environments (TEEs): page thrashing during the execution of convolutional layers and the decryption of…

Cryptography and Security · Computer Science 2021-10-01 Jean-Baptiste Truong , William Gallagher , Tian Guo , Robert J. Walls

Major winning Convolutional Neural Networks (CNNs), such as AlexNet, VGGNet, ResNet, GoogleNet, include tens to hundreds of millions of parameters, which impose considerable computation and memory overhead. This limits their practical use…

Computer Vision and Pattern Recognition · Computer Science 2023-04-28 Seyyed Hossein Hasanpour , Mohammad Rouhani , Mohsen Fayyaz , Mohammad Sabokrou

Large-scale subset selection asks for a small useful set of examples, features, sensors, seed users, or context passages from an enormous ground set. Submodular maximization is a canonical model for such diminishing-returns problems, but…

Data Structures and Algorithms · Computer Science 2026-05-07 Alan Kuhnle

Neural Networks accomplish amazing things, but they suffer from computational and memory bottlenecks that restrict their usage. Nowhere can this be better seen than in the mobile space, where specialized hardware is being created just to…

Computer Vision and Pattern Recognition · Computer Science 2019-04-15 Jon Hoffman

Edge computing for neural networks is getting important especially for low power applications and offline devices. TensorFlow Lite and PyTorch Mobile were released for this purpose. But they mainly support mobile devices instead of…

Hardware Architecture · Computer Science 2020-07-06 Hasan Unlu

The last decade has witnessed the breakthrough of deep neural networks (DNNs) in many fields. With the increasing depth of DNNs, hundreds of millions of multiply-and-accumulate (MAC) operations need to be executed. To accelerate such…

Hardware Architecture · Computer Science 2022-11-29 Amro Eldebiky , Grace Li Zhang , Georg Boecherer , Bing Li , Ulf Schlichtmann

Mixed-precision Deep Neural Networks achieve the energy efficiency and throughput needed for hardware deployment, particularly when the resources are limited, without sacrificing accuracy. However, the optimal per-layer bit precision that…

Machine Learning · Computer Science 2022-08-15 Mariam Rakka , Mohammed E. Fouda , Pramod Khargonekar , Fadi Kurdahi

We present MegaBlocks, a system for efficient Mixture-of-Experts (MoE) training on GPUs. Our system is motivated by the limitations of current frameworks, which restrict the dynamic routing in MoE layers to satisfy the constraints of…

Machine Learning · Computer Science 2022-11-30 Trevor Gale , Deepak Narayanan , Cliff Young , Matei Zaharia

This paper reduces the cost of DNNs training by decreasing the amount of data movement across heterogeneous architectures composed of several GPUs and multicore CPU devices. In particular, this paper proposes an algorithm to dynamically…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-04-07 Sicong Zhuang , Cristiano Malossi , Marc Casas

Modern machine learning accelerators are designed to efficiently execute deep neural networks (DNNs) by optimizing data movement, memory hierarchy, and compute throughput. However, emerging DNN models such as large language models, state…

Hardware Architecture · Computer Science 2025-09-03 Shubham Negi , Manik Singhal , Aayush Ankit , Sudeep Bhoja , Kaushik Roy

Dense linear layers are the dominant computational bottleneck in large neural networks, presenting a critical need for more efficient alternatives. Previous efforts focused on a small number of hand-crafted structured matrices and neglected…

Deep neural networks (DNNs) have become the state-of-the-art technique for machine learning tasks in various applications. However, due to their size and the computational complexity, large DNNs are not readily deployable on edge devices in…

Machine Learning · Computer Science 2018-05-31 Lazar Supic , Rawan Naous , Ranko Sredojevic , Aleksandra Faust , Vladimir Stojanovic

Deep convolutional neural networks have achieved remarkable success in computer vision. However, deep neural networks require large computing resources to achieve high performance. Although depthwise separable convolution can be an…

Computer Vision and Pattern Recognition · Computer Science 2019-09-06 Yunyang Xiong , Hyunwoo J. Kim , Varsha Hedau

In recent years, Mixture-of-Experts (MoE) has emerged as an effective approach for enhancing the capacity of deep neural network (DNN) with sub-linear computational costs. However, storing all experts on GPUs incurs significant memory…

Machine Learning · Computer Science 2025-03-11 Suraiya Tairin , Shohaib Mahmud , Haiying Shen , Anand Iyer

As the state-of-the-art machine learning methods in many fields rely on larger datasets, storing datasets and training models on them become significantly more expensive. This paper proposes a training set synthesis technique for…

Computer Vision and Pattern Recognition · Computer Science 2021-03-09 Bo Zhao , Konda Reddy Mopuri , Hakan Bilen

The memory consumption of most Convolutional Neural Network (CNN) architectures grows rapidly with increasing depth of the network, which is a major constraint for efficient network training on modern GPUs with limited memory, embedded…

Computer Vision and Pattern Recognition · Computer Science 2021-02-10 Bochen Guan , Jinnian Zhang , William A. Sethares , Richard Kijowski , Fang Liu

With the advent of deep learning, progressively larger neural networks have been designed to solve complex tasks. We take advantage of these capacity-rich models to lower the cost of inference by exploiting computation in superposition. To…

Machine Learning · Computer Science 2023-12-06 Nicolas Menet , Michael Hersche , Geethan Karunaratne , Luca Benini , Abu Sebastian , Abbas Rahimi

A standard hardware bottleneck when training deep neural networks is GPU memory. The bulk of memory is occupied by caching intermediate tensors for gradient computation in the backward pass. We propose a novel method to reduce this…

Computer Vision and Pattern Recognition · Computer Science 2023-03-03 Joya Chen , Kai Xu , Yuhui Wang , Yifei Cheng , Angela Yao

Memory is increasingly often the bottleneck when training neural network models. Despite this, techniques to lower the overall memory requirements of training have been less widely studied compared to the extensive literature on reducing…

Machine Learning · Computer Science 2022-04-12 Nimit S. Sohoni , Christopher R. Aberger , Megan Leszczynski , Jian Zhang , Christopher Ré

Mixture-of-Experts (MoE) language models can reduce computational costs by 2-4$\times$ compared to dense models without sacrificing performance, making them more efficient in computation-bounded scenarios. However, MoE models generally…

Machine Learning · Computer Science 2024-04-09 Bowen Pan , Yikang Shen , Haokun Liu , Mayank Mishra , Gaoyuan Zhang , Aude Oliva , Colin Raffel , Rameswar Panda