REVIEW 6 cited by
The Surprising Agreement Between Convex Optimization Theory and Learning-Rate Scheduling for Large Model Training
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
The Surprising Agreement Between Convex Optimization Theory and Learning-Rate Scheduling for Large Model Training
read the original abstract
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.
Forward citations
Cited by 6 Pith papers
-
A Defense of the Quadratic Model
Local Taylor-expanded quadratic models reproduce a 150M-parameter LLM's validation loss for up to 10% of training late in the run, and LLM pretraining operates within a factor of 2 of a stochastic or deterministic edg...
-
AGNFormer I: Reconstruction of AGN spectra using a probabilistic transformer model
An uncertainty-aware transformer reconstructs masked AGN broad lines and spectral halves with 4-16% flux errors and beats eleven purpose-built Lyα-reconstruction algorithms on a blind benchmark.
-
WSqD: A Horizon-Free Learning Rate Schedule for Large Model Training
WSqD uses a horizon-independent shifted inverse-square-root base plus linear cooldown to get optimal last-iterate rates in convex stochastic optimization and match or beat tuned WSD on LLM pretraining with one reused ...
-
Optimistic Dual Averaging Unifies Modern Optimizers
SODA unifies several modern optimizers under optimistic dual averaging and supplies a 1/k decay wrapper that improves performance without weight decay tuning.
-
Anytime Training with Schedule-Free Spectral Optimization
SF-NorMuon is a new schedule-free spectral optimizer that closes the gap with tuned AdamW on 125M-772M parameter models across 1-8x Chinchilla horizons while providing stationarity guarantees.
-
Why Do We Need Warm-up? A Theoretical Perspective
Under the proposed (H0,H1)-smoothness condition, gradient descent with a warm-up-style adaptive step-size provably converges faster than with any fixed step-size.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.