A solvable hierarchical model with power-law feature strengths yields explicit power-law scaling of prediction error through sequential recovery of latent directions by a layer-wise spectral algorithm.
arXiv preprint arXiv:2603.14573 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
Rigorous high-temperature free energy limit for the SYK model established via random graph components and cavity method, matching physics heuristics.
Quantitative quenched propagation of chaos holds for Langevin spin glass dynamics with non-Gaussian i.i.d. disorder satisfying T2, yielding explicit Wasserstein convergence rates and concentration bounds.
citing papers explorer
-
Scaling Laws from Sequential Feature Recovery: A Solvable Hierarchical Model
A solvable hierarchical model with power-law feature strengths yields explicit power-law scaling of prediction error through sequential recovery of latent directions by a layer-wise spectral algorithm.
-
The free energy limit of the SYK model at high temperature
Rigorous high-temperature free energy limit for the SYK model established via random graph components and cavity method, matching physics heuristics.
-
Quantitative propagation of chaos and universality for asymmetric Langevin spin glass dynamics
Quantitative quenched propagation of chaos holds for Langevin spin glass dynamics with non-Gaussian i.i.d. disorder satisfying T2, yielding explicit Wasserstein convergence rates and concentration bounds.