Seminar series
Date
Wed, 20 Apr 2022
Time
09:00 -
10:00
Location
Virtual
Speaker
Wei Chen
Organisation
Chinese Academy of Sciences
In this talk, I will introduce our investigations on how to make deep learning easier to optimize, faster to train, and more robust to out-of-distribution prediction. To be specific, we design a group-invariant optimization framework for ReLU neural networks; we compensate the gradient delay in asynchronized distributed training; and we improve the out-of-distribution prediction by incorporating “causal” invariance.