AI & ML
Transport-Free Lower Bounds for Ollivier--Ricci Curvature in Higher-Order Networks: Scope, Tightness, and Computational Applications
arXiv stat.ML0 views
arXiv:2405.13302v2 Announce Type: replace Abstract: We study how the Bauer--Jost--Liu curvature bound applies to hypergraph Ollivier--Ricci curvature (ORC) and how its accuracy depends on local mass and geometry. An explicit weighted-graph representation shows how the graph theorem applies. A transport construction transfers the bounds to monotone pairwise hyperedge aggregations. We analyze endpoint cancellation under laziness, quantify the exact improvement over the earlier mixture bound, and characterize the extremal geometry at fixed endpoint and overlap statistics. Further results quantify worst-case slack, stability, and exactness on isolated hyperedges. A capacity-constrained short-detour refinement uses additional geometric information and improves monotonically as the query budget increases. As a computational application, a threshold cascade preserves exact transport decisions. Numerical verification and public-hypergraph experiments examine tightness, walk dependence, and aggregation, including evaluations on 42,940 finite pairwise comparisons and 64,620 public-data instances. Together, the results specify the scope, equality mechanisms, and computational uses of BJL-type hypergraph bounds.
Source:https://arxiv.org/abs/2405.13302PreviousGradient Descent on Two ReLU Neurons: Global Landscape and Bifurcation DynamicsNextCritically-Damped Higher-Order Langevin Dynamics for Generative Modeling
Related posts
Most voted crypto projects on Coinvote, Oct 26 to Nov 1, 2026
0dev.to Data
Bluesky This Week — trending topics & AI brand mentions (2026-11-02)
0dev.to Data
Gemini 4 Carbon e DeepSeek V4.1 Flash Cyber: a Guerra Cibernética Autônoma e o Topo do Artificial Analysis
0dev.to Machine Learning
What can an AI agent do for you every day?
0dev.to Machine Learning
Mon modèle de paris semblait excellent sur 3 671 prédictions. Il n'a jamais battu le bookmaker.
0dev.to Machine Learning
HR manager LinkedIn About section examples you can adapt
0dev.to Career