DeepAI AI Chat
Log In Sign Up

Statistical and computational thresholds for the planted k-densest sub-hypergraph problem

by   Luca Corinzia, et al.

Recovery a planted signal perturbed by noise is a fundamental problem in machine learning. In this work, we consider the problem of recovery a planted k-densest sub-hypergraph on h-uniform hypergraphs over n nodes. This fundamental problem appears in different contexts, e.g., community detection, average case complexity, and neuroscience applications. We first observe that it can be viewed as a structural variant of tensor PCA in which the hypergraph parameters k and h determine the structure of the signal to be recovered when the observations are contaminated by Gaussian noise. In this work, we provide tight information-theoretic upper and lower bounds for the recovery problem, as well as the first non-trivial algorithmic bounds based on approximate message passing algorithms. The problem exhibits a typical information-to-computational-gap observed in analogous settings, that widens with increasing sparsity of the problem. Interestingly, the bounds show that the structure of the signal does have an impact on the existing bounds of tensor PCA that the unstructured planted signal does not capture.


Information Theoretic Limits of Exact Recovery in Sub-hypergraph Models for Community Detection

In this paper, we study the information theoretic bounds for exact recov...

Community Detection in the Hypergraph SBM: Optimal Recovery Given the Similarity Matrix

Community detection is a fundamental problem in network science. In this...

Submatrix localization via message passing

The principal submatrix localization problem deals with recovering a K× ...

Information Limits for Detecting a Subhypergraph

We consider the problem of recovering a subhypergraph based on an observ...

Algorithmic thresholds for tensor PCA

We study the algorithmic thresholds for principal component analysis of ...

Multilayer hypergraph clustering using the aggregate similarity matrix

We consider the community recovery problem on a multilayer variant of th...

Robust Group Synchronization via Cycle-Edge Message Passing

We propose a general framework for group synchronization with adversaria...