The Surprising Agreement Between Convex Optimization Theory and Learning-Rate Scheduling for Large Model Training
Paper
•
2501.18965
•
Published
•
5
Alexander Hägele
haeggee
AI & ML interests
None yet
Recent Activity
authored
a paper
8 months ago
Scaling Laws and Compute-Optimal Training Beyond Fixed Training
Durations
Organizations
haeggee's activity
authored
a
paper
3 days ago
authored
a
paper
8 months ago