Tensor Recovery in High-Dimensional Ising Models
Preprint
Abstract
The $k$-tensor Ising model is an exponential family on a $p$-dimensional binary hypercube for modeling dependent binary data, where the sufficient statistic consists of all $k$-fold products of the observations, and the parameter is an unknown $k$-fold tensor, designed to capture higher-order interactions between the binary variables. In this paper, we describe an approach based on a penalization technique that helps us recover the signed support of the tensor parameter with high probability, assuming that no entry of the true tensor is too close to zero. The method is based on an $\ell_1$-regularized node-wise logistic regression, that recovers the signed neighborhood of each node with high probability. Our analysis is carried out in the high-dimensional regime, that allows the dimension $p$ of the Ising model, as well as the interaction factor $k$ to potentially grow to $\infty$ with the sample size $n$. We show that if the minimum interaction strength is not too small, then consistent recovery of the entire signed support is possible if one takes $n = Ω((k!)^8 d^3 \log \binom{p-1}{k-1})$ samples, where $d$ denotes the maximum degree of the hypernetwork in question. Our results are validated in two simulation settings, and applied on a real neurobiological dataset consisting of multi-array electro-physiological recordings from the mouse visual cortex, to model higher-order interactions between the brain regions.
Keywords
All Related Versions
This publication has 29 references indexed in Scilit:
- Hypergraphs for predicting essential genes using multiprotein complex dataJournal of Complex Networks, 2021
- A large-scale standardized physiological survey reveals functional organization of the mouse visual cortexNature Neuroscience, 2019
- Ising models for neural activity inferred via selective cluster expansion: structural and coding propertiesJournal of Statistical Mechanics: Theory and Experiment, 2013
- Hypergraph with sampling for image retrievalPattern Recognition, 2011
- Using Rich Social Media Information for Music Recommendation via Hypergraph Model2011
- The spread of innovations in social networksProceedings of the National Academy of Sciences, 2010
- A hypergraph-based learning algorithm for classifying gene expression and arrayCGH data with prior knowledgeBioinformatics, 2009
- Notes on ferromagnetic p‐spin and REMMathematical Methods in the Applied Sciences, 2008
- Spin glasses with p-spin interactionsNuclear Physics B, 1985
- Neural networks and physical systems with emergent collective computational abilities.Proceedings of the National Academy of Sciences of the United States of America, 1982