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.
Backpropagation applied to handwritten zip code recognition.Neural computation, 1(4):541– 551
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
roles
dataset 1polarities
use dataset 1representative citing papers
citing papers explorer
-
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.
- From Per-Image Low-Rank to Encoding Mismatch: Rethinking Feature Distillation in Vision Transformers