Non-adaptive Learning of Random Hypergraphs with Queries

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Austhof, Bethany, Reyzin, Lev, Tani, Erasmo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917899463032832
author Austhof, Bethany
Reyzin, Lev
Tani, Erasmo
author_facet Austhof, Bethany
Reyzin, Lev
Tani, Erasmo
contents We study the problem of learning a hidden hypergraph $G=(V,E)$ by making a single batch of queries (non-adaptively). We consider the hyperedge detection model, in which every query must be of the form: ``Does this set $S\subseteq V$ contain at least one full hyperedge?'' In this model, it is known that there is no algorithm that allows to non-adaptively learn arbitrary hypergraphs by making fewer than $Ω(\min\{m^2\log n, n^2\})$ even when the hypergraph is constrained to be $2$-uniform (i.e. the hypergraph is simply a graph). Recently, Li et al. overcame this lower bound in the setting in which $G$ is a graph by assuming that the graph learned is sampled from an Erdős-Rényi model. We generalize the result of Li et al. to the setting of random $k$-uniform hypergraphs. To achieve this result, we leverage a novel equivalence between the problem of learning a single hyperedge and the standard group testing problem. This latter result may also be of independent interest.
format Preprint
id arxiv_https___arxiv_org_abs_2501_12771
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Non-adaptive Learning of Random Hypergraphs with Queries
Austhof, Bethany
Reyzin, Lev
Tani, Erasmo
Information Theory
Discrete Mathematics
Data Structures and Algorithms
Machine Learning
We study the problem of learning a hidden hypergraph $G=(V,E)$ by making a single batch of queries (non-adaptively). We consider the hyperedge detection model, in which every query must be of the form: ``Does this set $S\subseteq V$ contain at least one full hyperedge?'' In this model, it is known that there is no algorithm that allows to non-adaptively learn arbitrary hypergraphs by making fewer than $Ω(\min\{m^2\log n, n^2\})$ even when the hypergraph is constrained to be $2$-uniform (i.e. the hypergraph is simply a graph). Recently, Li et al. overcame this lower bound in the setting in which $G$ is a graph by assuming that the graph learned is sampled from an Erdős-Rényi model. We generalize the result of Li et al. to the setting of random $k$-uniform hypergraphs. To achieve this result, we leverage a novel equivalence between the problem of learning a single hyperedge and the standard group testing problem. This latter result may also be of independent interest.
title Non-adaptive Learning of Random Hypergraphs with Queries
topic Information Theory
Discrete Mathematics
Data Structures and Algorithms
Machine Learning
url https://arxiv.org/abs/2501.12771