AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Nonparametric Modeling of Higher-Order Interactions via Hypergraphons

Krishnakumar Balasubramanian

JMLR 2021 · Learning theory and algorithms › Sample complexity · approach: Density and property estimation · 7 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use hypergraphon estimator instead of C3MM when 70% of hyperedges observedhyperedge prediction · GPS (70% observed)AUC: 0.69 -> 0.73Improved
use hypergraphon estimator instead of C3MM when 70% of hyperedges observedhyperedge prediction · MovieLens (70% observed)AUC: 0.81 -> 0.85Improved
use hypergraphon estimator instead of C3MM at 90% observedhyperedge prediction · GPS (90% observed)AUC: 0.83 -> 0.82No clear effect
use hypergraphon estimator instead of C3MM at 90% observedhyperedge prediction · MovieLens (90% observed)AUC: 0.90 -> 0.90No clear effect
use hypergraphon estimator instead of CMM at 70% observedhyperedge prediction · GPS (70% observed)AUC: 0.64 -> 0.73Improved
use spectral instead of random initialization (ablation)SLH estimator · dense simulation (rho=1)normalized L2 reconstruction errorNo clear effect
use spectral instead of random initialization (ablation)SLH estimator · sparse simulation (rho=0.7)normalized L2 reconstruction errorImproved
increase number of nodes n at fixed k (ablation)SLH estimator · well-specified simulationnormalized L2 reconstruction errorImproved
use rank-1 hypergraphon f=uvw (case 1) rather than logistic case 2SLH estimator · well-specified simulationnormalized L2 reconstruction errorImproved
increase number of blocks k from 0.1n^3 to 0.9n^3 (ablation)SLH estimator · simulation n=20 densenormalized L2 reconstruction errorMixed
increase p1,q1 (richer misspecified hypergraphon)SLH estimator · misspecified simulation n=100normalized L2 reconstruction error: 0.2 -> 0.8Hurt
set p2 equal to q2 (constant hypergraphon)SLH estimator · misspecified simulation n=100normalized L2 reconstruction errorImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy