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 2301.12809cs.LGcs.AIcs.PF
收藏

纯16位浮点神经网络的隐藏力量

The Hidden Power of Pure 16-bit Floating-Point Neural Networks

Stony Brook University(石溪大学);State University of New York Korea(韩国全州大学(韩国分校))

Juyoung Yun, Byungkon Kang, Zhoulai Fu

AI总结:

本文研究了纯16位浮点神经网络在分类任务中相比32位网络出人意料的性能提升,通过大量实验和理论分析验证了其效率优势,并指出了低精度训练有害的情形。

摘要:

尽管在空间和时间上有所收益,但将神经网络从普遍使用的32位精度降低长期以来一直被认为会损害性能。许多工作提出了各种技术来实现半精度神经网络,但没有研究纯16位设置。本文研究了纯16位神经网络在分类任务中相对于32位网络出人意料的性能提升。我们提供了大量的实验结果,将各种16位神经网络的性能与32位模型进行了有利的比较。此外,我们还提供了对16位模型效率的理论分析,并辅以经验证据加以支持。最后,我们讨论了低精度训练确实有害的情况。

英文摘要:

Lowering the precision of neural networks from the prevalent 32-bit precision has long been considered harmful to performance, despite the gain in space and time. Many works propose various techniques to implement half-precision neural networks, but none study pure 16-bit settings. This paper investigates the unexpected performance gain of pure 16-bit neural networks over the 32-bit networks in classification tasks. We present extensive experimental results that favorably compare various 16-bit neural networks' performance to those of the 32-bit models. In addition, a theoretical analysis of the efficiency of 16-bit models is provided, which is coupled with empirical evidence to back it up. Finally, we discuss situations in which low-precision training is indeed detrimental.

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。

↑