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

Fabian S, Alexander Hägele, Adrien Taylor, Umut Simsekli, Francis Bach

The Surprising Agreement Between Convex Optimization Theory and Learning-Rate Scheduling for Large Model Training: 7 upvotes on Hugging Face Daily Papers, #10 of 16 papers on 2025-02-03. Day-by-day upvote history.

We show that learning-rate schedules for large model training behave surprisingly similar to a performance bound from non-smooth convex optimization theory. We provide a bound for the constant schedule with linear cooldown; in particular, the practical benefit of cooldown is reflected in the bound due to the absence of logarithmic terms. Further, we show that this surprisingly close match between optimization theory and practice can be exploited for learning-rate tuning: we achieve noticeable improvements for training 124M and 210M Llama-type models by (i) extending the schedule for continued training with optimal learning-rate, and (ii) transferring the optimal learning-rate across schedules.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.