English
Related papers

Related papers: Training Deep Nets with Sublinear Memory Cost

200 papers

To train deep convolutional neural networks, the input data and the intermediate activations need to be kept in memory to calculate the gradient descent step. Given the limited memory available in the current generation accelerator cards,…

Computer Vision and Pattern Recognition · Computer Science 2018-04-17 Hans Pinckaers , Geert Litjens

In this paper, we propose training very deep neural networks (DNNs) for supervised learning of hash codes. Existing methods in this context train relatively "shallow" networks limited by the issues arising in back propagation (e.e.…

Computer Vision and Pattern Recognition · Computer Science 2016-04-25 Ziming Zhang , Yuting Chen , Venkatesh Saligrama

Typically, Ultra-deep neural network(UDNN) tends to yield high-quality model, but its training process is usually resource intensive and time-consuming. Modern GPU's scarce DRAM capacity is the primary bottleneck that hinders the…

Machine Learning · Computer Science 2019-06-21 Jinrong Guo , Wantao Liu , Wang Wang , Qu Lu , Songlin Hu , Jizhong Han , Ruixuan Li

Large-scale deep neural networks (DNN) have been successfully used in a number of tasks from image recognition to natural language processing. They are trained using large training sets on large models, making them computationally and…

Machine Learning · Computer Science 2017-03-28 Sek Chai , Aswin Raghavan , David Zhang , Mohamed Amer , Tim Shields

Recomputation algorithms collectively refer to a family of methods that aims to reduce the memory consumption of the backpropagation by selectively discarding the intermediate results of the forward propagation and recomputing the discarded…

Machine Learning · Computer Science 2019-05-29 Mitsuru Kusumoto , Takuya Inoue , Gentaro Watanabe , Takuya Akiba , Masanori Koyama

Training convolutional neural network models is memory intensive since back-propagation requires storing activations of all intermediate layers. This presents a practical concern when seeking to deploy very deep architectures in production,…

Machine Learning · Computer Science 2019-10-30 Ayan Chakrabarti , Benjamin Moseley

In this paper, we study the problem of improving computational resource utilization of neural networks. Deep neural networks are usually over-parameterized for their tasks in order to achieve good performances, thus are likely to have…

Computer Vision and Pattern Recognition · Computer Science 2018-12-04 Siyuan Qiao , Zhe Lin , Jianming Zhang , Alan Yuille

Residual neural networks can be viewed as the forward Euler discretization of an Ordinary Differential Equation (ODE) with a unit time step. This has recently motivated researchers to explore other discretization approaches and train ODE…

Machine Learning · Computer Science 2019-07-02 Amir Gholami , Kurt Keutzer , George Biros

The ever-growing computational demands of increasingly complex machine learning models frequently necessitate the use of powerful cloud-based infrastructure for their training. Binary neural networks are known to be promising candidates for…

This paper develops a new neural network architecture for modeling spatial distributions (i.e., distributions on R^d) which is computationally efficient and specifically designed to take advantage of the spatial structure of limit order…

Trading and Market Microstructure · Quantitative Finance 2016-07-06 Justin Sirignano

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…

It is known that $O(N)$ parameters are sufficient for neural networks to memorize arbitrary $N$ input-label pairs. By exploiting depth, we show that $O(N^{2/3})$ parameters suffice to memorize $N$ pairs, under a mild condition on the…

Machine Learning · Computer Science 2021-11-03 Sejun Park , Jaeho Lee , Chulhee Yun , Jinwoo Shin

Designing energy-efficient networks is of critical importance for enabling state-of-the-art deep learning in mobile and edge settings where the computation and energy budgets are highly limited. Recently, Liu et al. (2019) framed the search…

Machine Learning · Computer Science 2020-07-10 Dilin Wang , Meng Li , Lemeng Wu , Vikas Chandra , Qiang Liu

We propose a novel method for training a neural network for image classification to reduce input data dynamically, in order to reduce the costs of training a neural network model. As Deep Learning tasks become more popular, their…

Machine Learning · Computer Science 2025-10-10 Dominic Sanderson , Tatiana Kalgonova

Deep Neural Networks(DNNs) require huge GPU memory when training on modern image/video databases. Unfortunately, the GPU memory is physically finite, which limits the image resolutions and batch sizes that could be used in training for…

Machine Learning · Computer Science 2021-03-22 Jianwei Feng , Dong Huang

Neural network training requires a large amount of computation and thus GPUs are often used for the acceleration. While they improve the performance, GPUs are underutilized during the training.This paper proposes out-of-order (ooo)…

Machine Learning · Computer Science 2021-10-05 Hyungjun Oh , Hyungjun Oh , HyeongJu Kim , Jiwon Seo

We present an approach to adaptively utilize deep neural networks in order to reduce the evaluation time on new examples without loss of accuracy. Rather than attempting to redesign or approximate existing networks, we propose two schemes…

Machine Learning · Computer Science 2017-09-20 Tolga Bolukbasi , Joseph Wang , Ofer Dekel , Venkatesh Saligrama

The success of deep neural networks (DNNs) is attributable to three factors: increased compute capacity, more complex models, and more data. These factors, however, are not always present, especially for edge applications such as autonomous…

Computer Vision and Pattern Recognition · Computer Science 2019-08-26 Bichen Wu

Deep graph neural networks (GNNs) have achieved excellent results on various tasks on increasingly large graph datasets with millions of nodes and edges. However, memory complexity has become a major obstacle when training deep GNNs for…

Machine Learning · Computer Science 2022-04-12 Guohao Li , Matthias Müller , Bernard Ghanem , Vladlen Koltun

Deep learning is slowly, but steadily, hitting a memory bottleneck. While the tensor computation in top-of-the-line GPUs increased by 32x over the last five years, the total available memory only grew by 2.5x. This prevents researchers from…

Machine Learning · Computer Science 2021-04-06 Aashaka Shah , Chao-Yuan Wu , Jayashree Mohan , Vijay Chidambaram , Philipp Krähenbühl