arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.05137cs.LG
收藏

层输入中的Quantization是物质

Quantization in Layer's Input is Matter

Daning Cheng, WenGuang Chen

摘要:

在本文中,我们将证明在层的输入量化比参数的量化更重要的损失函数。基于层输入量化误差的算法优于基于海森的混合精度布局算法。

英文摘要:

In this paper, we will show that the quantization in layer's input is more important than parameters' quantization for loss function. And the algorithm which is based on the layer's input quantization error is better than hessian-based mixed precision layout algorithm.

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。

↑