[Adapt] [seminar] Low-rank Matrix Decomposition for Model Compression

[任思宇]

Hi Adapters,

In recent years, model compression has enjoyed vast amout of attention due to the prevelance of large pre-trained models. The aim of model compression is to creat compact(i.e., fast and small) yet performant model to support time-sensitive and resource-constrained application scenarios. Today I will talk about low-rank matrix decomposition, which is one type of model compression techenique.


Hope you find it useful!


Time: Wed 4:00 pm
Venue: SEIEE 3-414
Best Regards,
Roy
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://cs.sjtu.edu.cn/pipermail/adapt/attachments/20220223/95d4d65a/attachment.htm>