Neural Scaling Laws Rooted in the Data Distribution
read the original abstract
Deep neural networks exhibit empirical neural scaling laws, with error decreasing as a power law with increasing model or data size, across a wide variety of architectures, tasks, and datasets. This universality suggests that scaling laws may result from general properties of natural learning tasks. We develop a mathematical model intended to describe natural datasets using percolation theory. Two distinct criticality regimes emerge, each yielding optimal power-law neural scaling laws. These regimes, corresponding to power-law-distributed discrete subtasks and a dominant data manifold, can be associated with previously proposed theories of neural scaling, thereby grounding and unifying prior works. We test the theory by training regression models on toy datasets derived from percolation theory simulations. We suggest directions for quantitatively predicting language model scaling.
This paper has not been read by Pith yet.
Forward citations
Cited by 4 Pith papers
-
Smooth Scaling Laws Hide Stepwise Token Learning
Token loss trajectories follow localized sigmoids whose learning-time spectrum quantitatively reconstructs scaling-law derivatives on T, D, and M axes and enables faster training via distribution reshaping.
-
Critical Percolation as a Synthetic Data Model for Interpretability
Critical percolation clusters embedded in high dimensions, combined with taxonomic latent variables, form an analytically tractable synthetic data model whose ground-truth hierarchy can be linearly decoded from networ...
-
Practical Scaling Laws: Converting Compute into Performance in a Data-Constrained World
A new scaling law L(N, D, T) = E + (L0 - E) h/(1+h) with h = a/N^α + b/T^β + c N^γ/D^δ that decomposes loss into undercapacity, undertraining, and overfitting terms and saturates between E and L0.
-
Superposition Yields Robust Neural Scaling
Strong superposition causes neural loss to scale as the inverse of model dimension due to geometric feature overlaps, explaining scaling laws for broad frequency distributions.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.