Degree Heterogeneity in Higher-Order Networks: Inference in the Hypergraph $\boldsymbolβ$-Model

• URL: http://arxiv.org/abs/2307.02818v4
• Date: Wed, 5 Jun 2024 19:00:23 GMT
• Title: Degree Heterogeneity in Higher-Order Networks: Inference in the Hypergraph $\boldsymbolβ$-Model
• Authors: Sagnik Nandy, Bhaswar B. Bhattacharya,
• Abstract summary: We study the hypergraph $boldsymbolbeta$-model with multiple layers, which allows for hyperedges of different sizes across the layers. We derive the rates of convergence of maximum likelihood (ML) estimates and establish their minimax rate optimality. We also consider the goodness-of-fit problem in the hypergraph $boldsymbolbeta$-model.
• Score: 4.540236408836132
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The $\boldsymbol{\beta}$-model for random graphs is commonly used for representing pairwise interactions in a network with degree heterogeneity. Going beyond pairwise interactions, Stasi et al. (2014) introduced the hypergraph $\boldsymbol{\beta}$-model for capturing degree heterogeneity in networks with higher-order (multi-way) interactions. In this paper we initiate the rigorous study of the hypergraph $\boldsymbol{\beta}$-model with multiple layers, which allows for hyperedges of different sizes across the layers. To begin with, we derive the rates of convergence of the maximum likelihood (ML) estimate and establish their minimax rate optimality. We also derive the limiting distribution of the ML estimate and construct asymptotically valid confidence intervals for the model parameters. Next, we consider the goodness-of-fit problem in the hypergraph $\boldsymbol{\beta}$-model. Specifically, we establish the asymptotic normality of the likelihood ratio (LR) test under the null hypothesis, derive its detection threshold, and also its limiting power at the threshold. Interestingly, the detection threshold of the LR test turns out to be minimax optimal, that is, all tests are asymptotically powerless below this threshold. The theoretical results are further validated in numerical experiments. In addition to developing the theoretical framework for estimation and inference for hypergraph $\boldsymbol{\beta}$-models, the above results fill a number of gaps in the graph $\boldsymbol{\beta}$-model literature, such as the minimax optimality of the ML estimates and the non-null properties of the LR test, which, to the best of our knowledge, have not been studied before.

Related papers

• Minimax Hypothesis Testing for the Bradley-Terry-Luce Model [6.5990719141691825]
  The Bradley-Terry-Luce (BTL) model is one of the most widely used models for ranking a collection of items or agents. We propose a hypothesis test that determines whether a given pairwise comparison dataset, with $k$ comparisons per pair of agents, originates from an underlying BTL model.
  arXiv  Detail & Related papers  (2024-10-10T20:28:05Z)
• Convergence Analysis of Probability Flow ODE for Score-based Generative Models [5.939858158928473]
  We study the convergence properties of deterministic samplers based on probability flow ODEs from both theoretical and numerical perspectives. We prove the total variation between the target and the generated data distributions can be bounded above by $mathcalO(d3/4delta1/2)$ in the continuous time level.
  arXiv  Detail & Related papers  (2024-04-15T12:29:28Z)
• Maximum Mean Discrepancy Meets Neural Networks: The Radon-Kolmogorov-Smirnov Test [5.255750357176021]
  We study the function of $mathcalF$ to be the unit ball in the RBV space of a given smoothness order $k geq 0$. This test can be viewed as a generalization of the well-known and classical Kolmogorov-Smirnov (KS) test to multiple dimensions and higher orders of smoothness. We leverage the power of modern deep learning toolkits to optimize the criterion that underlies the RKS test.
  arXiv  Detail & Related papers  (2023-09-05T17:51:00Z)
• Towards Faster Non-Asymptotic Convergence for Diffusion-Based Generative Models [49.81937966106691]
  We develop a suite of non-asymptotic theory towards understanding the data generation process of diffusion models. In contrast to prior works, our theory is developed based on an elementary yet versatile non-asymptotic approach.
  arXiv  Detail & Related papers  (2023-06-15T16:30:08Z)
• Detection of Dense Subhypergraphs by Low-Degree Polynomials [72.4451045270967]
  Detection of a planted dense subgraph in a random graph is a fundamental statistical and computational problem. We consider detecting the presence of a planted $Gr(ngamma, n-alpha)$ subhypergraph in a $Gr(n, n-beta) hypergraph. Our results are already new in the graph case $r=2$, as we consider the subtle log-density regime where hardness based on average-case reductions is not known.
  arXiv  Detail & Related papers  (2023-04-17T10:38:08Z)
• Statistical Limits for Testing Correlation of Hypergraphs [4.898744396854313]
  We consider the hypothesis testing of correlation between two $m$-uniform hypergraphs on $n$ unlabelled nodes. Under the null hypothesis, the hypergraphs are independent, while under the alternative hypothesis, the hyperdges have the same marginal distributions as in the null hypothesis but are correlated after some unknown node permutation.
  arXiv  Detail & Related papers  (2022-02-11T20:11:21Z)
• Polyak-Ruppert Averaged Q-Leaning is Statistically Efficient [90.14768299744792]
  We study synchronous Q-learning with Polyak-Ruppert averaging (a.k.a., averaged Q-leaning) in a $gamma$-discounted MDP. We establish normality for the iteration averaged $barboldsymbolQ_T$. In short, our theoretical analysis shows averaged Q-Leaning is statistically efficient.
  arXiv  Detail & Related papers  (2021-12-29T14:47:56Z)
• The Performance of the MLE in the Bradley-Terry-Luce Model in $\ell_{\infty}$-Loss and under General Graph Topologies [76.61051540383494]
  We derive novel, general upper bounds on the $ell_infty$ estimation error of the Bradley-Terry-Luce model. We demonstrate that the derived bounds perform well and in some cases are sharper compared to known results.
  arXiv  Detail & Related papers  (2021-10-20T23:46:35Z)
• Tightening the Dependence on Horizon in the Sample Complexity of Q-Learning [59.71676469100807]
  This work sharpens the sample complexity of synchronous Q-learning to an order of $frac|mathcalS|| (1-gamma)4varepsilon2$ for any $0varepsilon 1$. Our finding unveils the effectiveness of vanilla Q-learning, which matches that of speedy Q-learning without requiring extra computation and storage.
  arXiv  Detail & Related papers  (2021-02-12T14:22:05Z)
• Rates of convergence for density estimation with generative adversarial networks [19.71040653379663]
  We prove an oracle inequality for the Jensen-Shannon (JS) divergence between the underlying density $mathsfp*$ and the GAN estimate. We show that the JS-divergence between the GAN estimate and $mathsfp*$ decays as fast as $(logn/n)2beta/ (2beta + d)$.
  arXiv  Detail & Related papers  (2021-01-30T09:59:14Z)
• Sample Complexity of Asynchronous Q-Learning: Sharper Analysis and Variance Reduction [63.41789556777387]
  Asynchronous Q-learning aims to learn the optimal action-value function (or Q-function) of a Markov decision process (MDP) We show that the number of samples needed to yield an entrywise $varepsilon$-accurate estimate of the Q-function is at most on the order of $frac1mu_min (1-gamma)5varepsilon2+ fract_mixmu_min (1-gamma)$ up to some logarithmic factor.
  arXiv  Detail & Related papers  (2020-06-04T17:51:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.