#geometric-analysis2 articles

2 articles

AINeutralarXiv – CS AI · 5h ago

🧠

A Geometric Perspective on the Difficulties of Learning GNN-based SAT Solvers

Researchers explain why Graph Neural Networks (GNNs) struggle with complex Boolean Satisfiability Problems (SATs) through geometric analysis using graph Ricci Curvature. They prove that harder SAT instances have more negative curvature, creating connectivity bottlenecks that prevent GNNs from effectively processing long-range dependencies.

AINeutralarXiv – CS AI · 5h ago

🧠

Directional Neural Collapse Explains Few-Shot Transfer in Self-Supervised Learning

Researchers propose directional CDNV (decision-axis variance) as a key geometric quantity explaining why self-supervised learning representations transfer well with few labels. The study shows that small variability along class-separating directions enables strong few-shot transfer and low interference across multiple tasks.