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.
Deep learning face attributes in the wild
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
A proxy model with adaptive constrained optimization enables non-adversarial minimization of the Jeffreys divergence, producing more stable and accurate distribution fitting than MLE or GANs especially in low-data regimes.
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.
-
Adaptive Symmetrization of the KL Divergence
A proxy model with adaptive constrained optimization enables non-adversarial minimization of the Jeffreys divergence, producing more stable and accurate distribution fitting than MLE or GANs especially in low-data regimes.