arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1910.02558cs.LGstat.ML
收藏

突破RNN压缩的极限

Pushing the limits of RNN Compression

AMD Research(AMD研究院);Arm ML Research Lab(Arm机器学习研究实验室)

Urmish Thakker, Igor Fedorov, Jesse Beu, Dibakar Gope, Chu Zhou, Ganesh Dasika, Matthew Mattina

摘要:

递归神经网络(RNN)由于其大小而难以部署在资源受限的设备上。因此,需要一种可以显著压缩RNN而不会对任务准确性产生负面影响的压缩技术。本文介绍了一种利用Kronecker积(KP)对资源受限环境下的RNN进行压缩的方法。KPs可以将RNN层压缩16- 38倍,精度损失最小。我们表明,KP可以在跨越3个不同应用程序的4个基准测试中击败其他最先进的压缩技术(修剪和低秩矩阵分解)所实现的任务准确性,同时提高推理运行时间。

英文摘要:

Recurrent Neural Networks (RNN) can be difficult to deploy on resource constrained devices due to their size. As a result, there is a need for compression techniques that can significantly compress RNNs without negatively impacting task accuracy. This paper introduces a method to compress RNNs for resource constrained environments using Kronecker product (KP). KPs can compress RNN layers by 16-38x with minimal accuracy loss. We show that KP can beat the task accuracy achieved by other state-of-the-art compression techniques (pruning and low-rank matrix factorization) across 4 benchmarks spanning 3 different applications, while simultaneously improving inference run-time.

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。

↑