One geometric idea that explains SGD, AdamW, and Muon (kbwal.github.io) 1 points by kbwal7 9d ago ↗ HN
[–] crystalskies 9d ago ↗ What are your thoughts on some of the disadvantages of using Muon over AdamW?
3 comments
[ 0.23 ms ] story [ 8.5 ms ] thread