Metastability of the Potts Ferromagnet on Random Regular Graphs
We study the performance of Markov chains for the q-state ferromagnetic Potts model on random regular graphs. While the cases of the grid and the complete graph are by now well-understood, the case of random regular graphs has resisted a detailed analysis and, in fact, even analysing the properties of the Potts distribution has remained elusive. It is conjectured that the performance of Markov chains is dictated by metastability phenomena, i.e., the presence of "phases" (clusters) in the sample space where Markov chains with local update rules, such as the Glauber dynamics, are bound to take exponential time to escape, and therefore cause slow mixing. The phases that are believed to drive these metastability phenomena in the case of the Potts model emerge as local, rather than global, maxima of the so-called Bethe functional, and previous approaches of analysing these phases based on optimisation arguments fall short of the task.
Our first contribution is to detail the emergence of the metastable phases for the q-state Potts model on the d-regular random graph for all integers q,d ≥ 3, and establish that for an interval of temperatures, delineated by the uniqueness and a broadcasting threshold on the d-regular tree, the two phases coexist. The proofs are based on a conceptual connection between spatial properties and the structure of the Potts distribution on the random regular graph, rather than complicated moment calculations. This significantly refines earlier results by Helmuth, Jenssen, and Perkins who had established phase coexistence for a small interval around the so-called ordered-disordered threshold (via different arguments) that applied for large q and d ≥ 5.
Based on our new structural understanding of the model, we obtain various algorithmic consequences. We first complement recent fast mixing results for Glauber dynamics by Blanca and Gheissari below the uniqueness threshold, showing an exponential lower bound on the mixing time above the uniqueness threshold. Then, we obtain tight results even for the non-local and more elaborate Swendsen-Wang chain, where we establish slow mixing/metastability for the whole interval of temperatures where the chain is conjectured to mix slowly on the random regular graph. The key is to bound the conductance of the chains using a random graph "planting" argument combined with delicate bounds on random-graph percolation.
Markov chains
sampling
random regular graph
Potts model
Theory of computation~Random walks and Markov chains
45:1-45:20
Track A: Algorithms, Complexity and Games
https://arxiv.org/abs/2202.05777
Amin
Coja-Oghlan
Amin Coja-Oghlan
Faculty of Computer Science, TU Dortmund, Germany
supported by DFG CO 646/3 and 646/4.
Andreas
Galanis
Andreas Galanis
Department of Computer Science, University of Oxford, UK
Leslie Ann
Goldberg
Leslie Ann Goldberg
Department of Computer Science, University of Oxford, UK
Jean Bernoulli
Ravelomanana
Jean Bernoulli Ravelomanana
Faculty of Computer Science, TU Dortmund, Germany
supported by DFG CO 646/4.
Daniel
Štefankovič
Daniel Štefankovič
Department of Computer Science, Univerity of Rochester, NY, USA
supported by NSF grant CCF-2007287.
Eric
Vigoda
Eric Vigoda
Computer Science, University of California Santa Barbara, CA, USA
supported by NSF CCF-2007022.
10.4230/LIPIcs.ICALP.2022.45
Emmanuel Abbe. Community detection and stochastic block models: Recent developments. Journal of Maching Learning Research, 18(1):6446-6531, 2017.
Dimitris Achlioptas, Assaf Naor, and Yuval Peres. Rigorous location of phase transitions in hard optimization problems. Nature, 435(7043):759-764, 2005.
Victor Bapst and Amin Coja-Oghlan. Harnessing the Bethe free energy. Random Structures and Algorithms, 49:694-741, 2016.
Jean Barbier, Chun Lam Clement Chan, and Nicolas Macris. Concentration of multi-overlaps for random dilute ferromagnetic spin models. Journal of Statistical Physics, 180:534-557, 2019.
Antonio Blanca, Andreas Galanis, Leslie Ann Goldberg, erg, Daniel Štefankovič, Eric Vigoda, and Kuan Yang. Sampling in uniqueness from the Potts and random-cluster models on random regular graphs. SIAM Journal on Discrete Mathematics, 34(1):742-793, 2020.
Antonio Blanca and Reza Gheissari. Random-cluster dynamics on random regular graphs in tree uniqueness. Communications in Mathematical Physics, 386(2):1243-1287, 2021.
Antonio Blanca and Alistair Sinclair. Dynamics for the mean-field random-cluster model. In Approximation, Randomization, and Combinatorial Optimization. Algorithms and Techniques (APPROX/RANDOM), pages 528-543, 2015.
Antonio Blanca, Alistair Sinclair, and Xusheng Zhang. The critical mean-field Chayes-Machta dynamics. In Approximation, Randomization, and Combinatorial Optimization. Algorithms and Techniques (APPROX/RANDOM), 2021.
Magnus Bordewich, Catherine Greenhill, and Viresh Patel. Mixing of the Glauber dynamics for the ferromagnetic Potts model. Random Structures and Algorithms, 48(1):21-52, 2016.
Charlie Carlson, Ewan Davies, Nicolas Fraiman, Alexandra Kolla, Aditya Potukuchi, and Corrine Yap. Algorithms for the ferromagnetic Potts model on expanders. arXiv preprint, 2022. URL: http://arxiv.org/abs/2204.01923.
http://arxiv.org/abs/2204.01923
Amin Coja-Oghlan, Oliver Cooley, Mihyun Kang, Joon Lee, and Jean Bernoulli Ravelomanana. The sparse parity matrix. In Proceedings of the 2022 Annual ACM-SIAM Symposium on Discrete Algorithms (SODA), pages 822-833, 2022.
Amin Coja-Oghlan, Charilaos Efthymiou, and Samuel Hetterich. On the chromatic number of random regular graphs. Journal of Combinatorial Theory, Series B, 116:367-439, 2016.
Amin Coja-Oghlan, Charilaos Efthymiou, Nor Jaafari, Mihyun Kang, and Tobias Kapetanopoulos. Charting the replica symmetric phase. Communications in Mathematical Physics, 359(2):603-698, 2018.
Amin Coja-Oghlan, Oliver Gebhard, Max Hahn-Klimroth, and Philipp Loick. Optimal group testing. Combinatorics, Probability and Computing, 30(6):811-848, 2021.
Amin Coja-Oghlan, Florent Krzakala, Will Perkins, and Lenka Zdeborová. Information-theoretic thresholds from the cavity method. Advances in Mathematics, 333:694-795, 2018.
Amin Coja-Oghlan, Philipp Loick, Balázs F Mezei, and Gregory B Sorkin. The Ising antiferromagnet and max cut on random regular graphs. arXiv preprint, 2020. URL: http://arxiv.org/abs/2009.10483.
http://arxiv.org/abs/2009.10483
Paul Cuff, Jian Ding, Oren Louidor, Eyal Lubetzky, Yuval Peres, and Allan Sly. Glauber dynamics for the mean-field Potts model. Journal of Statistical Physics, 149(3):432-477, 2012.
Amir Dembo and Andrea Montanari. Ising models on locally tree-like graphs. The Annals of Applied Probability, 20(2):565-592, 2010.
Amir Dembo, Andrea Montanari, Allan Sly, and Nike Sun. The replica symmetric solution for Potts models on d-regular graphs. Communications in Mathematical Physics, 327(2):551-575, 2014.
Amir Dembo, Andrea Montanari, and Nike Sun. Factor models on locally tree-like graph. The Annals of Probability, 41(6):4162-4213, 2013.
Charilaos Efthymiou. On sampling symmetric Gibbs distributions on sparse random graphs and hypergraphs. arXiv preprint, 2020. URL: http://arxiv.org/abs/2007.07145.
http://arxiv.org/abs/2007.07145
Andreas Galanis, Daniel Stefankovic, Eric Vigoda, and Linji Yang. Ferromagnetic Potts model: Refined #BIS-hardness and related results. SIAM Journal of Computation, 45(6):2004-2065, 2016.
Andreas Galanis, Daniel Štefankovič, and Eric Vigoda. Swendsen-Wang algorithm on the mean-field Potts model. Random Structures and Algorithms, 54(1):82-147, 2019.
Reza Gheissari and Eyal Lubetzky. Mixing times of critical two-dimensional Potts models. Communications on Pure and Applied Mathematics, 71(5):994-1046, 2018.
Reza Gheissari, Eyal Lubetzky, and Yuval Peres. Exponentially slow mixing in the mean-field Swendsen-Wang dynamics. In Proceedings of the Twenty-Ninth Annual ACM-SIAM Symposium on Discrete Algorithms (SODA), 2018.
Reza Gheissari and Alistair Sinclair. Low-temperature Ising dynamics with random initializations. arXiv preprint, 2021. URL: http://arxiv.org/abs/2106.11296.
http://arxiv.org/abs/2106.11296
Vivek K Gore and Mark R Jerrum. The Swendsen-Wang process does not always mix rapidly. Journal of Statistical Physics, 97(1):67-86, 1999.
Olle Häggström. The random-cluster model on a homogeneous tree. Probability Theory and Related Fields, 104(2):231-253, 1996.
Tyler Helmuth, Matthew Jenssen, and Will Perkins. Finite-size scaling, phase coexistence, and algorithms for the random cluster model on random graphs. arXiv preprint, 2020. URL: http://arxiv.org/abs/2006.11580.
http://arxiv.org/abs/2006.11580
Svante Janson, Andrzej Rucinski, and Tomasz Luczak. Random graphs. John Wiley and Sons, 2011.
Jungkyoung Lee. Energy landscape and metastability of curie-weiss-potts model. Journal of Statistical Physics, 187(1):1-46, 2022.
David A Levin and Yuval Peres. Markov chains and mixing times. American Mathematical Society, 2009.
Eyal Lubetzky and Allan Sly. Critical Ising on the square lattice mixes in polynomial time. Communications in Mathematical Physics, 313(3):815-836, 2012.
Marc Mézard. Mean-field message-passing equations in the Hopfield model and its generalizations. Physical Review E, 95(2):022117, 2017.
Marc Mezard and Andrea Montanari. Information, physics, and computation. Oxford University Press, 2009.
Marc Mézard and Giorgio Parisi. The Bethe lattice spin glass revisited. The European Physical Journal B-Condensed Matter and Complex Systems, 20(2):217-233, 2001.
Marc Mézard and Giorgio Parisi. The cavity method at zero temperature. Journal of Statistical Physics, 111(1):1-34, 2003.
Tom Richardson and Ruediger Urbanke. Modern coding theory. Cambridge University Press, 2008.
Nicholas Ruozzi. The bethe partition function of log-supermodular graphical models. Advances in Neural Information Processing Systems, 25, 2012.
Allan Sly. Computational transition at the uniqueness threshold. In 51st Annual IEEE Symposium on Foundations of Computer Science (FOCS), pages 287-296, 2010.
Allan Sly and Nike Sun. The computational hardness of counting in two-spin models on d-regular graphs. In 53rd Annual IEEE Symposium on Foundations of Computer Science (FOCS), pages 361-369, 2012.
Mario Ullrich. Swendsen-Wang is faster than single-bond dynamics. SIAM Journal on Discrete Mathematics, 28(1):37-48, 2014.
Pascal O Vontobel. Counting in graph covers: A combinatorial characterization of the Bethe entropy function. IEEE Transactions on Information Theory, 59(9):6018-6048, 2013.
Jonathan S Yedidia, William T Freeman, and Yair Weiss. Understanding belief propagation and its generalizations. Exploring artificial intelligence in the new millennium, 8:239-269, 2003.
Amin Coja-Oghlan, Andreas Galanis, Leslie Ann Goldberg, Jean Bernoulli Ravelomanana, Daniel Štefankovič, and Eric Vigoda
Creative Commons Attribution 4.0 International license
https://creativecommons.org/licenses/by/4.0/legalcode