Almanac
paper

How Width and Data Shape Generalization Scaling Laws in Quadratic Neural Networks

paperactiveprovisionalhow-width-and-data-shape-generalization-scaling-laws-in-quadratic-neural-networks-e4ecebd7·1 events·first seen 17h ago

Aliases: How Width and Data Shape Generalization Scaling Laws in Quadratic Neural Networks

More like this (12)

Recent events (1)

5arXiv · cs.AI·17h ago·source ↗

Theoretical analysis of generalization scaling laws in quadratic two-layer neural networks

A new arXiv preprint derives explicit characterizations of generalization error as a joint function of model width, sample count, and regularization in a quadratic two-layer network with structured data. The analysis reveals a phase diagram with distinct scaling regimes governed by data-dependent power laws tied to the spectral structure of the target function. The work extends scaling law theory beyond fixed-feature or infinite-width regimes by operating in a finite-sample, feature-learning setting, and characterizes interpolation threshold transitions.