Nonparametric Modeling of Higher-Order Interactions via Hypergraphons
arXiv:2105.08678
Abstract
We study statistical and algorithmic aspects of using hypergraphons, that are limits of large hypergraphs, for modeling higher-order interactions. Although hypergraphons are extremely powerful from a modeling perspective, we consider a restricted class of Simple Lipschitz Hypergraphons (SLH), that are amenable to practically efficient estimation. We also provide rates of convergence for our estimator that are optimal for the class of SLH. Simulation results are provided to corroborate the theory.
arXiv commentTo appear in Journal of Machine Learning Research
References in corpus (21)
- Community detection in graphs
- Spectral redemption: clustering sparse networks
- Matrix estimation by Universal Singular Value Thresholding
- Random hypergraphs and their applications
- Stochastic blockmodels with growing number of classes
- Rate-optimal graphon estimation
- Sparse graphs using exchangeable random measures
- Coauthorship and Citation Networks for Statisticians
- Nonparametric graphon estimation
- Alignment and integration of complex networks by hypergraph-based spectral clustering
- Hypergraph topological quantities for tagged social networks
- Consistency of Spectral Hypergraph Partitioning under Planted Partition Model
- Hypergraph Spectral Clustering in the Weighted Stochastic Block Model
- Statistical and Computational Guarantees of Lloyd's Algorithm and its Variants
- Community Detection for Hypergraph Networks via Regularized Tensor Power Iteration
- A Consistent Histogram Estimator for Exchangeable Graph Models
- Stochastic Block Model for Hypergraphs: Statistical limits and a semidefinite programming approach
- Sampling perspectives on sparse exchangeable graphs
- models for random hypergraphs with a given degree sequence
- Model-free consistency of graph partitioning
- Hierarchical network models for structured exchangeable interaction processes