REVIEW 5 cited by
Learning Curves for SGD on Structured Features
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
read the original abstract
The generalization performance of a machine learning algorithm such as a neural network depends in a non-trivial way on the structure of the data distribution. To analyze the influence of data structure on test loss dynamics, we study an exactly solveable model of stochastic gradient descent (SGD) on mean square loss which predicts test loss when training on features with arbitrary covariance structure. We solve the theory exactly for both Gaussian features and arbitrary features and we show that the simpler Gaussian model accurately predicts test loss of nonlinear random-feature models and deep neural networks trained with SGD on real datasets such as MNIST and CIFAR-10. We show that the optimal batch size at a fixed compute budget is typically small and depends on the feature correlation structure, demonstrating the computational benefits of SGD with small batch sizes. Lastly, we extend our theory to the more usual setting of stochastic gradient descent on a fixed subsampled training set, showing that both training and test error can be accurately predicted in our framework on real data.
Forward citations
Cited by 5 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...
-
Universal One-third Time Scaling in Learning Peaked Distributions
Softmax + cross-entropy on peaked targets yields loss ∼ t^{−1/3}, giving an architecture-driven explanation for power-law LLM training time without power-law data.
-
Scaling Law for Stochastic Gradient Descent in Quadratically Parameterized Linear Regression
For power-law data and target decays, SGD on the quadratically parameterized model provably beats linear SGD when the target opposes the spectrum, with rates T^{-(2β-2)/(α+β)} versus T^{-(β-1)/α}.
-
Seesaw: Accelerating Training by Balancing Learning Rate and Batch Size Scheduling
When a cosine schedule would halve the learning rate, Seesaw cuts it by √2 and doubles the batch, matching loss curves with ~36% fewer serial steps.
-
Unifying Learning Dynamics and Generalization in Transformers Scaling Law
Claims a two-stage transformer scaling law (exponential then C^{-1/6}) with matching bounds, but the lower bounds are missing, the exponent is inconsistent (-1/7 vs -1/6), and the law is an artifact of hand-set M = Θ(...
Discussion (0). Continue with ORCID to comment.