Saved in:
Bibliographic Details
Main Authors: Even, Bertrand, Giraud, Christophe, Verzelen, Nicolas
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2402.18378
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909122810609664
author Even, Bertrand
Giraud, Christophe
Verzelen, Nicolas
author_facet Even, Bertrand
Giraud, Christophe
Verzelen, Nicolas
contents We investigate the existence of a fundamental computation-information gap for the problem of clustering a mixture of isotropic Gaussian in the high-dimensional regime, where the ambient dimension $p$ is larger than the number $n$ of points. The existence of a computation-information gap in a specific Bayesian high-dimensional asymptotic regime has been conjectured by arXiv:1610.02918 based on the replica heuristic from statistical physics. We provide evidence of the existence of such a gap generically in the high-dimensional regime $p \geq n$, by (i) proving a non-asymptotic low-degree polynomials computational barrier for clustering in high-dimension, matching the performance of the best known polynomial time algorithms, and by (ii) establishing that the information barrier for clustering is smaller than the computational barrier, when the number $K$ of clusters is large enough. These results are in contrast with the (moderately) low-dimensional regime $n \geq poly(p, K)$, where there is no computation-information gap for clustering a mixture of isotropic Gaussian. In order to prove our low-degree computational barrier, we develop sophisticated combinatorial arguments to upper-bound the mixed moments of the signal under a Bernoulli Bayesian model.
format Preprint
id arxiv_https___arxiv_org_abs_2402_18378
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Computation-information gap in high-dimensional clustering
Even, Bertrand
Giraud, Christophe
Verzelen, Nicolas
Statistics Theory
62H30
We investigate the existence of a fundamental computation-information gap for the problem of clustering a mixture of isotropic Gaussian in the high-dimensional regime, where the ambient dimension $p$ is larger than the number $n$ of points. The existence of a computation-information gap in a specific Bayesian high-dimensional asymptotic regime has been conjectured by arXiv:1610.02918 based on the replica heuristic from statistical physics. We provide evidence of the existence of such a gap generically in the high-dimensional regime $p \geq n$, by (i) proving a non-asymptotic low-degree polynomials computational barrier for clustering in high-dimension, matching the performance of the best known polynomial time algorithms, and by (ii) establishing that the information barrier for clustering is smaller than the computational barrier, when the number $K$ of clusters is large enough. These results are in contrast with the (moderately) low-dimensional regime $n \geq poly(p, K)$, where there is no computation-information gap for clustering a mixture of isotropic Gaussian. In order to prove our low-degree computational barrier, we develop sophisticated combinatorial arguments to upper-bound the mixed moments of the signal under a Bernoulli Bayesian model.
title Computation-information gap in high-dimensional clustering
topic Statistics Theory
62H30
url https://arxiv.org/abs/2402.18378