Neural LoFi models deep learning as layer-wise spectral filtering that selects maximal low-degree correlations, yielding a tractable surrogate for hierarchical representation learning beyond the lazy regime.
& Wyart, M.How compositional generalization and creativity improve as diffusion models are traineden
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 2
method 1
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4representative citing papers
Generative diffusion and flow models are constructed to remain exactly on the Lorentz-invariant massless N-particle phase space manifold during sampling for particle physics applications.
Gradient flow in energy-based models for strictly positive binary distributions produces stable data-consistent fixed points and a learning hierarchy that favors lower-order interactions first, mechanistically explaining distributional simplicity bias.
Diffusion models exhibit a distributional simplicity bias, learning pairwise input statistics at linear sample complexity while fourth-order cumulants require cubic complexity unless sharing correlated latent structure.
citing papers explorer
-
Deep Learning as Neural Low-Degree Filtering: A Spectral Theory of Hierarchical Feature Learning
Neural LoFi models deep learning as layer-wise spectral filtering that selects maximal low-degree correlations, yielding a tractable surrogate for hierarchical representation learning beyond the lazy regime.
-
Distributional simplicity bias and effective convexity in Energy Based Models
Gradient flow in energy-based models for strictly positive binary distributions produces stable data-consistent fixed points and a learning hierarchy that favors lower-order interactions first, mechanistically explaining distributional simplicity bias.