arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1802.01616cs.LG
收藏

稀疏化深度神经网络的重加权学习

Re-Weighted Learning for Sparsifying Deep Neural Networks

Department of Electrical;Computer Engineering University of California, San-Diego

Igor Fedorov, Bhaskar D. Rao

摘要:

本文讨论了稀疏化深度神经网络(DNN)的主题。虽然DNN是在大量任务上实现最先进性能的强大模型,但大量模型参数带来了严重的存储和计算挑战。为了克服这些困难,越来越多的工作专注于在不牺牲性能的情况下修剪网络权重。我们提出了一种通用的仿射尺度变换(AST)算法来稀疏DNN。我们的方法遵循流行的稀疏恢复技术的脚步,这些技术尚未在DNN的背景下进行探索。我们描述了一个原则性的框架,用于在不牺牲网络性能的情况下将密集连接的DNN转换为稀疏连接的DNN。与现有方法不同,我们的方法能够同时学习每一层的稀疏连接,并在测试的架构上实现相当的修剪结果。

英文摘要:

This paper addresses the topic of sparsifying deep neural networks (DNN's). While DNN's are powerful models that achieve state-of-the-art performance on a large number of tasks, the large number of model parameters poses serious storage and computational challenges. To combat these difficulties, a growing line of work focuses on pruning network weights without sacrificing performance. We propose a general affine scaling transformation (AST) algorithm to sparsify DNN's. Our approach follows in the footsteps of popular sparse recovery techniques, which have yet to be explored in the context of DNN's. We describe a principled framework for transforming densely connected DNN's into sparsely connected ones without sacrificing network performance. Unlike existing methods, our approach is able to learn sparse connections at each layer simultaneously, and achieves comparable pruning results on the architecture tested.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑