Sublinearly structured DNNs attain feature-learning consistency and universal approximation for hierarchically compositional functions, with popular CNNs fitting this structure on image benchmarks.
arXiv:2009.09535 , primaryClass=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Denoising-GS reformulates 3DGS optimization as primitive denoising using spatial gradient consistency, uncertainty pruning, and coherence refinement to boost novel view synthesis fidelity.
citing papers explorer
-
Sublinearly Structured Deep Neural Networks Achieve Feature Learning Consistency for Compositional Functions
Sublinearly structured DNNs attain feature-learning consistency and universal approximation for hierarchically compositional functions, with popular CNNs fitting this structure on image benchmarks.
-
Denoising-GS: Gaussian Splatting with Spatial-aware Denoising
Denoising-GS reformulates 3DGS optimization as primitive denoising using spatial gradient consistency, uncertainty pruning, and coherence refinement to boost novel view synthesis fidelity.