Anirbit
@anirbit.bsky.social
Assistant Professor/Lecturer in ML @ The University of Manchester | https://anirbit-ai.github.io/ | working on the theory of neural nets and how they solve differential equations. #AI4SCIENCE
Thanks. No, AutoSGD is not going as far as delta-GClip goes. It's Theorem 4.5 is where they have any global minima convergence happening - but it uses assumptions which are not known to be true for nets. Our convergence holds for *all* nets wide enough.
July 1, 2025 at 10:42 AM
Thanks. No, AutoSGD is not going as far as delta-GClip goes. It's Theorem 4.5 is where they have any global minima convergence happening - but it uses assumptions which are not known to be true for nets. Our convergence holds for *all* nets wide enough.
Do link to the paper! I can have a look and check.
July 1, 2025 at 9:02 AM
Do link to the paper! I can have a look and check.