REVIEW 6 cited by
A Dynamical Model of Neural Scaling Laws
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
abstract
On a variety of tasks, the performance of neural networks predictably improves with training time, dataset size and model size across many orders of magnitude. This phenomenon is known as a neural scaling law. Of fundamental importance is the compute-optimal scaling law, which reports the performance as a function of units of compute when choosing model sizes optimally. We analyze a random feature model trained with gradient descent as a solvable model of network training and generalization. This reproduces many observations about neural scaling laws. First, our model makes a prediction about why the scaling of performance with training time and with model size have different power law exponents. Consequently, the theory predicts an asymmetric compute-optimal scaling rule where the number of training steps are increased faster than model parameters, consistent with recent empirical observations. Second, it has been observed that early in training, networks converge to their infinite-width dynamics at a rate $1/\textit{width}$ but at late time exhibit a rate $\textit{width}^{-c}$, where $c$ depends on the structure of the architecture and task. We show that our model exhibits this behavior. Lastly, our theory shows how the gap between training and test loss can gradually build up over time due to repeated reuse of data.
Forward citations
Cited by 6 Pith papers
-
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 Collapse Reveals Universal Dynamics in Compute-Optimally Trained Neural Networks
Compute-optimally trained networks of different sizes show loss curves that collapse onto one universal curve after normalization; with learning rate decay, the collapse is tighter than seed-to-seed noise, providing a...
-
Scaling Laws and Spectra of Shallow Neural Networks in the Feature Learning Regime
For diagonal and quadratic two-layer networks, training maps to LASSO and matrix compressed sensing, yielding a full phase diagram of excess-risk scaling exponents and a spectral characterization of the trained weights.
-
Models of Heavy-Tailed Mechanistic Universality
A new random matrix model with one structure parameter explains heavy-tailed spectra in trained networks, and yields scaling laws, optimizer-tail behavior, and a description of the five-plus-one phases of training.
-
X-Factor: Quality Is a Dataset-Intrinsic Property
Across 2,500 class-balanced MNIST subsets and 10 model architectures, test-error Z-scores correlate strongly across models (mean R2=0.82 excluding GNB), supporting dataset quality as an intrinsic property.
-
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.