paper-with-me

홈 › Papers

ReSprop: Reuse Sparsified Backpropagation

2020-06-01 · CVPR 2020 6 · Negar Goli, Tor M. Aamodt

The success of Convolutional Neural Networks (CNNs) in various applications is accompanied by a significant increase in computation and training time. In this work, we focus on accelerating training by observing that about 90% of gradients are reusable during training. Leveraging this observation, we propose a new algorithm, Reuse-Sparse-Backprop (ReSprop), as a method to sparsify gradient vectors during CNN training. ReSprop maintains state-of-the-art accuracy on CIFAR-10, CIFAR-100, and ImageNet datasets with less than 1.1% accuracy loss while enabling a reduction in back-propagation computations by a factor of 10x resulting in a 2.7x overall speedup in training. As the computation reduction introduced by Re-Sprop is accomplished by introducing fine-grained sparsity that reduces computation efficiency on GPUs, we introduce a generic sparse convolution neural network accelerator (GSCN), which is designed to accelerate sparse back-propagation convolutions. When combined with ReSprop, GSCN achieves 8.0x and 7.2x speedup in the backward pass on ResNet34 and VGG16 versus a GTX 1080 Ti GPU.

📄 PDF Abstract BibTeX

Code (1)

negargoli/ReSprop 공식 구현 pytorch

Tasks

GPU

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

SparseProp: Efficient Sparse Backpropagation for Faster Training of Neural Networks

2023-02-09 · Mahdi Nikdan, Tommaso Pegolotti, Eugenia Iofinova, Eldar Kurtic 외

We provide a new efficient version of the backpropagation algorithm, specialized to the case where the weights of the neural network being trained are sparse. Our algorithm is general, as it applies to arbitrary (unstruc…

Transfer Learning

On quantum backpropagation, information reuse, and cheating measurement collapse

2023-05-22 · NeurIPS 2023 11

The success of modern deep learning hinges on the ability to train neural networks at scale. Through clever reuse of intermediate information, backpropagation facilitates training through gradient computation at a total …

Quantum Machine Learning

Sparsified Model Zoo Twins: Investigating Populations of Sparsified Neural Network Models

2023-04-26 · Dominik Honegger, Konstantin Schürholt, Damian Borth

With growing size of Neural Networks (NNs), model sparsification to reduce the computational cost and memory demand for model inference has become of vital interest for both research and production. While many sparsifica…

Sheared Backpropagation for Fine-tuning Foundation Models

2024-01-01 · CVPR 2024 1 · Zhiyuan Yu, Li Shen, Liang Ding, Xinmei Tian 외

Fine-tuning is the process of extending the training of pre-trained models on specific target tasks thereby significantly enhancing their performance across various applications. However fine-tuning often demands lar…

Benchmarking

Timestep-Compressed Attack on Spiking Neural Networks through Timestep-Level Backpropagation

2025-08-19 · Donghwa Kang, Doohyun Kim, Sang-Ki Ko, Jinkyu Lee 외 arxiv

State-of-the-art (SOTA) gradient-based adversarial attacks on spiking neural networks (SNNs), which largely rely on extending FGSM and PGD frameworks, face a critical limitation: substantial attack latency from multi-tim…