> Partially Encrypted Deep Learning using Functional Encryption
I don't agree about this one. It does seem fundamental science to me.
And here we see the problem with this particular way of splitting. Although I agree NeurIPS needs to be split up somehow.
Encrypting deep learning is problem for practical applications that require privacy. That's applied science.
Well machine learning is applied science. But inside there are theoretical work (like encrypted machine learning or optimization theory) and practical work (like text2speech, or other tasks)
Disagree. Theory is always interested in building better, simpler protocols, asking questions about lower bounds and possibility. See almost all of fundamental crypto research.
How do you suppose you're going to provide theoretical assurance of privacy and correctness without science?
Maybe I'm wrong but I see this as applied vs fundamental, not "without science" issue.
Re:NeurIPS 2019 Notes [pdf]
by softwaredoug on Sunday December 22, 2019 @09:48AM
(#21857357)
Right I agree. I mean to try to explain why so many go to this conference, not to criticize the conference itself.
Science vs applications would be actually a good way to divide NeurIPS into two conferences to get focus back: NeurIPS and Applied NeurIPS. One wold present science, the other tweaks, tricks and methods to solve everyday problems.
Papers like "Partially Encrypted Deep Learning using Functional Encryption", "Dancing to Music", "Differentiable Cloth Simulation for Inverse Problems" would go go the engineering conference for the "most people".