
34:30
Have to head out — thank you!

51:21
Correct me if I am wrong, incase of overparametrized NNs , wouldn't the loss have a double descent?

52:12
Ok. Thanks!

01:17:14
Could you remind us which papers each of the sections of your talk was based on? Thanks.

01:17:36
I think this is the first one https://arxiv.org/pdf/2006.15812v1.pdf

01:26:12
actually I pasted the wrong link, sorry xD

01:26:51
https://arxiv.org/abs/1810.04207

01:27:09
great talk!!

01:27:09
Hardness for unit norm input and unit norm weightd