On the replica symmetry phase of the independent set problem
Nicola Kistler, Marius A. Schmidt

TL;DR
This paper rigorously analyzes the replica symmetry phase of the independent set problem on Erdős-Rényi graphs using statistical mechanics, establishing the free energy and conjecturing the ground state structure.
Contribution
It introduces a Hamiltonian framework for the ISP, rigorously proves the existence of a replica symmetry phase, and derives a conjectural formula for the ground state based on Parisi theory.
Findings
Established the free energy in the replica symmetry phase
Proved the existence of a replica symmetry phase rigorously
Derived a conjectural formula for the ground state
Abstract
The independent set problem, ISP for short, asks for the maximal number of vertices in a (large) graph which can be occupied such that none of them are neighbors. We address the question from a statistical mechanics perspective, in the case of Erdoes-Renyi random graphs. We thereby introduce a Hamiltonian penalizing configurations which do not satisfy the non-neighboring constraint: the ground state of the ensuing disordered system corresponds to the solution of the ISP. Identifying the ground state amounts, in turns, to control the phase where replica symmetry is broken, which is way beyond our current understanding. By means of Talagrand's cavity method, we rigorously establish the existence of a replica symmetry phase, computing, in particular, the free energy in the limit of large graphs. A conjectural formula for the ground state, hence for the solution of the ISP, is also derived.…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMarkov Chains and Monte Carlo Methods · Topological and Geometric Data Analysis · Stochastic processes and statistical mechanics
