Neural layers as stationary Schrödinger dynamics on latent graphs are shown equivalent to global supra-graph stationary systems, with coinciding hypothesis classes under strong-monotonicity assumptions and complexity bounds from graph geometry.
On the one hand, addition probability (for an edge e /∈ Et) of the true edge e ∈ Etrue is P true add (e) ≥ 1 − σ2 B∆2e , while for a spurious edge it is P spur add (e) ≤ σ2 B(∆′e)2
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Learning Latent Graph Geometry via Fixed-Point Schr\"odinger-Type Activation: A Theoretical Study
Neural layers as stationary Schrödinger dynamics on latent graphs are shown equivalent to global supra-graph stationary systems, with coinciding hypothesis classes under strong-monotonicity assumptions and complexity bounds from graph geometry.