Quadratic two-layer networks exhibit data-dependent power-law generalization scaling with distinct regimes in width and sample size, including an interpolation transition whose location depends on target spectrum.
Stationary points of shallow neural networks with quadratic activation function.arXiv preprint arXiv:1912.01599,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
How Width and Data Shape Generalization Scaling Laws in Quadratic Neural Networks
Quadratic two-layer networks exhibit data-dependent power-law generalization scaling with distinct regimes in width and sample size, including an interpolation transition whose location depends on target spectrum.