Pith. sign in

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

arxiv 2106.02713 v5 pith:RMUHOHSN submitted 2021-06-04 stat.ML cs.LG

classification stat.MLcs.LG
keywords featureslossstructuretestdatatrainingaccuratelyarbitrary
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. A Defense of the Quadratic Model

    cs.LG 2026-07 conditional novelty 7.0 of 10

    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...

  2. Universal One-third Time Scaling in Learning Peaked Distributions

    cs.LG 2026-02 conditional novelty 7.0 of 10

    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.

  3. Scaling Law for Stochastic Gradient Descent in Quadratically Parameterized Linear Regression

    cs.LG 2025-02 conditional novelty 7.0 of 10

    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}.

  4. Seesaw: Accelerating Training by Balancing Learning Rate and Batch Size Scheduling

    cs.LG 2025-10 conditional novelty 6.0 of 10

    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.

  5. Unifying Learning Dynamics and Generalization in Transformers Scaling Law

    cs.LG 2025-12 reject novelty 4.0 of 10

    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(...

Pith tools