News for hackers. Stuff that matters.
Re:Imitating Deep Learning Dynamics via Stochastic Different... by QuantumPain on Thursday October 14, 2021 @11:31PM (#28873901)
This reminded me of Invariant Risk Minimization (IRM) (https://arxiv.org/pdf/1907.02893.pdf) due to the linear bound being sufficient to control the features.

Do you have any comments/insight into how you’d say they’re similar/different? Thanks!

Re:Imitating Deep Learning Dynamics via Stochastic Different... by jiayaozhang on Thursday October 14, 2021 @11:47PM (#28874008)
Thanks for sharing the interesting IRM paper!

Will read and be back for discussion hopefully soon.