Fabian S

fabian-sp's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored a paper 7 months ago

The Surprising Agreement Between Convex Optimization Theory and Learning-Rate Scheduling for Large Model Training

Paper • 2501.18965 • Published Jan 31 • 7

authored 2 papers over 1 year ago

SGD with Clipping is Secretly Estimating the Median Gradient

Paper • 2402.12828 • Published Feb 20, 2024

MoMo: Momentum Models for Adaptive Learning Rates

Paper • 2305.07583 • Published May 12, 2023