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.
Computational thresholds in multi-modal learning via the spiked matrix-tensor model
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3roles
background 1polarities
background 1representative citing papers
A spiked signal-plus-noise model yields separation ratios that partition multimodal problems into four regimes where alignment, prediction, both, or neither succeed.
Introduces a TAP-motivated framework and constructs explicit parameter-free spectral algorithms that achieve strong detection and weak recovery thresholds in three canonical correlated two-view models with matching lower bounds.
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.
-
When to Align, When to Predict: A Phase Diagram for Multimodal Learning
A spiked signal-plus-noise model yields separation ratios that partition multimodal problems into four regimes where alignment, prediction, both, or neither succeed.
-
Optimal Spectral Algorithms for Correlated Two-view Models in High Dimensions
Introduces a TAP-motivated framework and constructs explicit parameter-free spectral algorithms that achieve strong detection and weak recovery thresholds in three canonical correlated two-view models with matching lower bounds.