Document Open Access Logo

On Sampling from Ising Models with Spectral Constraints

Authors Andreas Galanis, Alkis Kalavasis, Anthimos Vardis Kandiros

PDF
Thumbnail PDF

File

LIPIcs.APPROX-RANDOM.2024.70.pdf
  • Filesize: 0.74 MB
  • 14 pages

Document Identifiers

Author Details

Andreas Galanis
  • University of Oxford, UK
Alkis Kalavasis
  • Yale University, New Haven, CT, USA
Anthimos Vardis Kandiros
  • Massachusetts Institute of Technology, Cambridge, MA, USA

Funding

Vardis Kandiros was supported by a Fellowship of the Eric and Wendy Schmidt Center at the Broad Institute of MIT and Harvard and by the Onassis Foundation-Scholarship ID: F ZP 016-1/2019-2020.

Cite AsGet BibTex

Andreas Galanis, Alkis Kalavasis, and Anthimos Vardis Kandiros. On Sampling from Ising Models with Spectral Constraints. In Approximation, Randomization, and Combinatorial Optimization. Algorithms and Techniques (APPROX/RANDOM 2024). Leibniz International Proceedings in Informatics (LIPIcs), Volume 317, pp. 70:1-70:14, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)
https://doi.org/10.4230/LIPIcs.APPROX/RANDOM.2024.70

Abstract

We consider the problem of sampling from the Ising model when the underlying interaction matrix has eigenvalues lying within an interval of length γ. Recent work in this setting has shown various algorithmic results that apply roughly when γ < 1, notably with nearly-linear running times based on the classical Glauber dynamics. However, the optimality of the range of γ was not clear since previous inapproximability results developed for the antiferromagnetic case (where the matrix has entries ≤ 0) apply only for γ > 2. To this end, Kunisky (SODA'24) recently provided evidence that the problem becomes hard already when γ > 1 based on the low-degree hardness for an inference problem on random matrices. Based on this, he conjectured that sampling from the Ising model in the same range of γ is NP-hard. Here we confirm this conjecture, complementing in particular the known algorithmic results by showing NP-hardness results for approximately counting and sampling when γ > 1, with strong inapproximability guarantees; we also obtain a more refined hardness result for matrices where only a constant number of entries per row are allowed to be non-zero. The main observation in our reductions is that, for γ > 1, Glauber dynamics mixes slowly when the interactions are all positive (ferromagnetic) for the complete and random regular graphs, due to a bimodality in the underlying distribution. While ferromagnetic interactions typically preclude NP-hardness results, here we work around this by introducing in an appropriate way mild antiferromagnetism, keeping the spectrum roughly within the same range. This allows us to exploit the bimodality of the aforementioned graphs and show the target NP-hardness by adapting suitably previous inapproximability techniques developed for antiferromagnetic systems.

Subject Classification

ACM Subject Classification
  • Theory of computation → Problems, reductions and completeness
  • Theory of computation → Random walks and Markov chains
  • Theory of computation → Generating random combinatorial structures
Keywords
  • Ising model
  • spectral constraints
  • Glauber dynamics
  • mean-field Ising
  • random regular graphs

Metrics

  • Access Statistics
  • Total Accesses (updated on a weekly basis)
    0
    PDF Downloads
    0
    Metadata Views

Related Versions

References

  1. Vedat Levi Alev and Lap Chi Lau. Improved analysis of higher order random walks and applications. In Proceedings of the 52nd Annual ACM SIGACT Symposium on Theory of Computing, STOC 2020, pages 1198-1211, 2020. Google Scholar
  2. Paola Alimonti and Viggo Kann. Hardness of approximating problems on cubic graphs. In Proceedings of the Third Italian Conference on Algorithms and Complexity, CIAC '97, pages 288-298, 1997. Google Scholar
  3. Nima Anari, Vishesh Jain, Frederic Koehler, Huy Tuan Pham, and Thuy-Duong Vuong. Entropic independence in high-dimensional expanders: Modified log-sobolev inequalities for fractionally log-concave polynomials and the ising model. arXiv preprint, 10:32-42, 2021. URL: https://arxiv.org/abs/2106.04105.
  4. Nima Anari, Kuikui Liu, and Shayan Oveis Gharan. Spectral independence in high-dimensional expanders and applications to the hardcore model. In 2020 IEEE 61st Annual Symposium on Foundations of Computer Science (FOCS), pages 1319-1330, 2020. Google Scholar
  5. Afonso S Bandeira, Dmitriy Kunisky, and Alexander S Wein. Computational hardness of certifying bounds on constrained pca problems. In 11th Innovations in Theoretical Computer Science Conference (ITCS 2020), volume 151, page 78. Schloss Dagstuhl - Leibniz-Zentrum für Informatik, 2020. Google Scholar
  6. Ivona Bezáková, Andreas Galanis, Leslie Ann Goldberg, and Daniel Štefankovič. Fast sampling via spectral independence beyond bounded-degree graphs. ACM Trans. Algorithms, 20(1), January 2024. Google Scholar
  7. Rajendra Bhatia. Perturbation bounds for matrix eigenvalues. SIAM, 2007. Google Scholar
  8. Charles Bordenave. A new proof of friedman’s second eigenvalue theorem and its extension to random lifts. In Annales Scientifiques de l'École Normale Supérieure, volume 4, pages 1393-1439, 2020. Google Scholar
  9. Guy Bresler. Efficiently learning Ising models on arbitrary graphs. In Proceedings of the Forty-Seventh Annual ACM Symposium on Theory of Computing, STOC '15, pages 771-782, 2015. Google Scholar
  10. Yuansi Chen and Ronen Eldan. Localization schemes: A framework for proving mixing bounds for markov chains. In 2022 IEEE 63rd Annual Symposium on Foundations of Computer Science (FOCS), pages 110-122. IEEE, 2022. Google Scholar
  11. Zongchen Chen, Kuikui Liu, and Eric Vigoda. Optimal mixing of Glauber dynamics: entropy factorization via high-dimensional expansion. In Proceedings of the 53rd Annual ACM SIGACT Symposium on Theory of Computing, STOC 2021, pages 1537-1550, 2021. Google Scholar
  12. Yuval Dagan, Constantinos Daskalakis, Nishanth Dikkala, and Anthimos Vardis Kandiros. Learning Ising models from one or multiple samples. In Proceedings of the 53rd Annual ACM SIGACT Symposium on Theory of Computing, STOC 2021, pages 161-168, 2021. Google Scholar
  13. Amir Dembo and Andrea Montanari. Ising models on locally tree-like graphs. The Annals of Applied Probability, 20(2):565-592, 2010. Google Scholar
  14. Jian Ding, Eyal Lubetzky, and Yuval Peres. The mixing time evolution of glauber dynamics for the mean-field ising model. Communications in Mathematical Physics, 289(2):725-764, 2009. Google Scholar
  15. Martin Dyer, Leslie Ann Goldberg, Catherine Greenhill, and Mark Jerrum. The relative complexity of approximate counting problems. Algorithmica, 38:471-500, 2004. Google Scholar
  16. Charilaos Efthymiou and Kostas Zampetakis. On sampling diluted spin glasses using glauber dynamics. arXiv preprint, 2024. URL: https://arxiv.org/abs/2403.08921.
  17. Ahmed El Alaoui, Andrea Montanari, and Mark Sellke. Sampling from the sherrington-kirkpatrick gibbs measure via algorithmic stochastic localization. In 2022 IEEE 63rd Annual Symposium on Foundations of Computer Science (FOCS), pages 323-334. IEEE, 2022. Google Scholar
  18. Ronen Eldan, Frederic Koehler, and Ofer Zeitouni. A spectral condition for spectral gap: fast mixing in high-temperature ising models. Probability theory and related fields, 182(3):1035-1051, 2022. Google Scholar
  19. Weiming Feng, Heng Guo, and Jiaheng Wang. Swendsen-Wang dynamics for the ferromagnetic Ising model with external fields. Information and Computation, 294:105066, 2023. Google Scholar
  20. Joel Friedman. A proof of Alon’s second eigenvalue conjecture and related problems. American Mathematical Soc., 2008. Google Scholar
  21. Andreas Galanis, Daniel Štefankovič, and Eric Vigoda. Inapproximability of the partition function for the antiferromagnetic ising and hard-core models. Combinatorics, Probability and Computing, 25(4):500-559, 2016. Google Scholar
  22. Antoine Gerschenfeld and Andrea Montanari. Reconstruction for models on random graphs. In 2007 48th Annual IEEE Symposium on Foundations of Computer Science, pages 194-204, 2007. Google Scholar
  23. Leslie Ann Goldberg and Mark Jerrum. Approximating the partition function of the ferromagnetic Potts model. J. ACM, 59(5), 2012. Google Scholar
  24. Heng Guo and Mark Jerrum. Random cluster dynamics for the Ising model is rapidly mixing. The Annals of Applied Probability, 28(2):1292-1313, 2018. Google Scholar
  25. Linus Hamilton, Frederic Koehler, and Ankur Moitra. Information theoretic properties of markov random fields, and their algorithmic applications. In Advances in Neural Information Processing Systems, volume 30, 2017. Google Scholar
  26. Brice Huang, Andrea Montanari, and Huy Tuan Pham. Sampling from spherical spin glasses in total variation via algorithmic stochastic localization. arXiv preprint, 2024. URL: https://arxiv.org/abs/2404.15651.
  27. Vishesh Jain, Frederic Koehler, and Andrej Risteski. Mean-field approximation, convex hierarchies, and the optimality of correlation rounding: a unified perspective. In Proceedings of the 51st Annual ACM SIGACT Symposium on Theory of Computing, pages 1226-1236, 2019. Google Scholar
  28. Mark Jerrum and Alistair Sinclair. Polynomial-time approximation algorithms for the Ising model. SIAM Journal on computing, 22(5):1087-1116, 1993. Google Scholar
  29. Mark R. Jerrum, Leslie G. Valiant, and Vijay V. Vazirani. Random generation of combinatorial structures from a uniform distribution. Theoretical Computer Science, 43:169-188, 1986. Google Scholar
  30. Adam Klivans and Raghu Meka. Learning graphical models using multiplicative weights. In 2017 IEEE 58th Annual Symposium on Foundations of Computer Science (FOCS), pages 343-354, 2017. Google Scholar
  31. Frederic Koehler, Holden Lee, and Andrej Risteski. Sampling approximately low-rank ising models: Mcmc meets variational methods. In Conference on Learning Theory, pages 4945-4988. PMLR, 2022. Google Scholar
  32. Dmitriy Kunisky. Optimality of Glauber dynamics for general-purpose Ising model sampling and free energy approximation. In Proceedings of the 2024 Annual ACM-SIAM Symposium on Discrete Algorithms (SODA), pages 5013-5028, 2024. Google Scholar
  33. Steffen L Lauritzen. Graphical models, volume 17. Clarendon Press, 1996. Google Scholar
  34. David A Levin, Malwina J Luczak, and Yuval Peres. Glauber dynamics for the mean-field Ising model: cut-off, critical power law, and metastability. Probability Theory and Related Fields, 146:223-265, 2010. Google Scholar
  35. Liang Li, Pinyan Lu, and Yitong Yin. Correlation decay up to uniqueness in spin systems. In Proceedings of the twenty-fourth annual ACM-SIAM symposium on Discrete algorithms, pages 67-84, 2013. Google Scholar
  36. Kuikui Liu, Sidhanth Mohanty, Amit Rajaraman, and David X Wu. Fast mixing in sparse random Ising models. arXiv preprint, 2024. URL: https://arxiv.org/abs/2405.06616.
  37. Eyal Lubetzky and Allan Sly. Critical Ising on the square lattice mixes in polynomial time. Communications in Mathematical Physics, 313(3):815-836, 2012. Google Scholar
  38. Fabio Martinelli and Enzo Olivieri. Approach to equilibrium of Glauber dynamics in the one phase region: I. The attractive case. Communications in Mathematical Physics, 161(3):447-486, 1994. Google Scholar
  39. Fabio Martinelli and Enzo Olivieri. Approach to equilibrium of Glauber dynamics in the one phase region: II. The general case. Communications in Mathematical Physics, 161(3):487-514, 1994. Google Scholar
  40. Marc Mezard and Andrea Montanari. Information, physics, and computation. Oxford University Press, 2009. Google Scholar
  41. Marc Mézard, Giorgio Parisi, and Miguel Angel Virasoro. Spin glass theory and beyond: An Introduction to the Replica Method and Its Applications, volume 9. World Scientific Publishing Company, 1987. Google Scholar
  42. Andrea Montanari, Elchanan Mossel, and Allan Sly. The weak limit of Ising models on locally tree-like graphs. Probability Theory and Related Fields, 152:31-51, 2012. Google Scholar
  43. Elchanan Mossel and Allan Sly. Exact thresholds for Ising–Gibbs samplers on general graphs. The Annals of Probability, 41(1), 2013. Google Scholar
  44. Andrej Risteski. How to calculate partition functions using convex programming hierarchies: provable bounds for variational methods. In Conference on Learning Theory, pages 1402-1416. PMLR, 2016. Google Scholar
  45. Alistair Sinclair, Piyush Srivastava, and Marc Thurley. Approximation algorithms for two-state anti-ferromagnetic spin systems on bounded degree graphs. Journal of Statistical Physics, 155(4):666-686, 2014. Google Scholar
  46. Allan Sly. Computational transition at the uniqueness threshold. In 2010 IEEE 51st Annual Symposium on Foundations of Computer Science, pages 287-296. IEEE, 2010. Google Scholar
  47. Allan Sly and Nike Sun. The computational hardness of counting in two-spin models on d-regular graphs. In 2012 IEEE 53rd Annual Symposium on Foundations of Computer Science, pages 361-369. IEEE, 2012. Google Scholar
  48. Michel Talagrand. Mean field models for spin glasses: Volume I: Basic examples, volume 54. Springer Science & Business Media, 2010. Google Scholar
Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail
© 2023-2024 Schloss Dagstuhl – LZI GmbH Imprint Privacy Contact