jianlin.su
@Jianlin_S
Grad&Clip&EM is all you need @Kimi_Moonshot
Blog: , Cool Papers:
Interesting link:
가입 February 2025
21 팔로잉 중 11.6K 팬
Revisiting Convergence Results in Convex Optimization (VII)
- New identity quantitatively link weight averaging and learning rate decay
- discuss why uniform averaging loses to sliding, and why Schedule-Free still can't fully escape scheduling
더 보기
