Parallel Tempering for the planted clique problem

TL;DR

This paper demonstrates that the Parallel-Tempering algorithm can recover planted cliques and independent sets in polynomial time in the hard regime, challenging previous beliefs about computational limits.

Contribution

It applies Parallel-Tempering to the planted clique and independent set problems, showing polynomial scaling where no efficient algorithms were known.

Findings

PT shows polynomial time scaling in the hard regime for planted clique.

PT effectively recovers solutions in the sparse planted independent set model.

Numerical evidence suggests PT outperforms existing methods in these problems.

Abstract

The theoretical information threshold for the planted clique problem is $2\log_2(N)$, however no polynomial algorithm is known to recover a planted clique of size $O(N^{1/2-\epsilon})$, $\epsilon>0$. In this paper we will apply a standard method for the analysis of disordered models, the Parallel-Tempering (PT) algorithm, to the clique problem, showing numerically that its time-scaling in the hard region is indeed polynomial for the analyzed sizes. We also apply PT to a different but connected model, the Sparse Planted Independent Set problem. In this situation thresholds should be sharper and finite size corrections should be less important. Also in this case PT shows a polynomial scaling in the hard region for the recovery.