Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
153 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Optimality of Glauber dynamics for general-purpose Ising model sampling and free energy approximation (2307.12581v2)

Published 24 Jul 2023 in cs.DS, math-ph, math.MP, and math.PR

Abstract: Recently, Eldan, Koehler, and Zeitouni (2020) showed that Glauber dynamics mixes rapidly for general Ising models so long as the difference between the largest and smallest eigenvalues of the coupling matrix is at most $1 - \epsilon$ for any fixed $\epsilon > 0$. We give evidence that Glauber dynamics is in fact optimal for this "general-purpose sampling" task. Namely, we give an average-case reduction from hypothesis testing in a Wishart negatively-spiked matrix model to approximately sampling from the Gibbs measure of a general Ising model for which the difference between the largest and smallest eigenvalues of the coupling matrix is at most $1 + \epsilon$ for any fixed $\epsilon > 0$. Combined with results of Bandeira, Kunisky, and Wein (2019) that analyze low-degree polynomial algorithms to give evidence for the hardness of the former spiked matrix problem, our results in turn give evidence for the hardness of general-purpose sampling improving on Glauber dynamics. We also give a similar reduction to approximating the free energy of general Ising models, and again infer evidence that simulated annealing algorithms based on Glauber dynamics are optimal in the general-purpose setting.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (68)
  1. The computational complexity of linear optics. In Proceedings of the forty-third annual ACM symposium on Theory of computing, pages 333–342, 2011.
  2. An introduction to random matrices. Cambridge University Press, 2010.
  3. Entropic independence in high-dimensional expanders: Modified log-Sobolev inequalities for fractionally log-concave polynomials and the Ising model. arXiv preprint arXiv:2106.04105, 2021.
  4. Some rigorous results on the Sherrington-Kirkpatrick spin glass model. Communications in Mathematical Physics, 112(1):3–20, 1987.
  5. Sampling from the Sherrington-Kirkpatrick Gibbs measure via algorithmic stochastic localization. arXiv preprint arXiv:2203.05093, 2022.
  6. A very simple proof of the LSI for high temperature spin systems. Journal of Functional Analysis, 276(8):2582–2588, 2019.
  7. Phase transition of the largest eigenvalue for nonnull complex sample covariance matrices. The Annals of Probability, 33(5):1643–1697, 2005.
  8. Spectral planting and the hardness of refuting cuts, colorability, and communities in random graphs. In 34th Annual Conference on Learning Theory (COLT 2021), pages 410–473. PMLR, 2021.
  9. A nearly tight sum-of-squares lower bound for the planted clique problem. SIAM Journal on Computing, 48(2):687–735, 2019.
  10. Computational hardness of certifying bounds on constrained PCA problems. In 11th Innovations in Theoretical Computer Science Conference (ITCS 2020), volume 151, pages 78:1–78:29, 2020.
  11. Average-case integrality gap for non-negative principal component analysis. In Mathematical and Scientific Machine Learning, pages 153–171. PMLR, 2022.
  12. Eigenvalues of large sample covariance matrices of spiked population models. Journal of Multivariate Analysis, 97(6):1382–1408, 2006.
  13. High temperature asymptotics of orthogonal mean-field spin glasses. Journal of Statistical Physics, 162:63–80, 2016.
  14. Accelerating simulated annealing for the permanent and combinatorial counting problems. SIAM Journal on Computing, 37(5):1429–1454, 2008.
  15. Role of the interaction matrix in mean-field spin glass models. Physical Review E, 67(4):046112, 2003.
  16. Michael Celentano. Sudakov-Fernique post-AMP, and a new proof of the local convexity of the TAP free energy. arXiv preprint arXiv:2208.09550, 2022.
  17. F Comets. A spherical bound for the Sherrington-Kirkpatrick model. Asterisque, 236:103–108, 1996.
  18. Non-gaussian component analysis via lattice basis reduction. In Conference on Learning Theory, pages 4535–4547. PMLR, 2022.
  19. PL Dobrushin. The description of a random field by means of conditional probabilities and conditions of its regularity. Theory of Probability & Its Applications, 13(2):197–224, 1968.
  20. A spectral condition for spectral gap: Fast mixing in high-temperature Ising models. arXiv preprint arXiv:2007.08200, 2020.
  21. TAP equations for orthogonally invariant spin glasses at high temperature. arXiv preprint arXiv:2202.09325, 2022.
  22. The replica-symmetric free energy for Ising spin glasses with orthogonally invariant couplings. arXiv preprint arXiv:2105.02797, 2021.
  23. Low-degree hardness of random optimization problems. In 61st Annual Symposium on Foundations of Computer Science (FOCS 2020), pages 131–140, 2020.
  24. Alice Guionnet and M Maıda. A Fourier view on the R𝑅Ritalic_R-transform and related asymptotics of spherical integrals. Journal of Functional Analysis, 222(2):435–490, 2005.
  25. Inapproximability for antiferromagnetic spin systems in the tree nonuniqueness region. Journal of the ACM (JACM), 62(6):1–60, 2015.
  26. Inapproximability of the partition function for the antiferromagnetic Ising and hard-core models. Combinatorics, Probability and Computing, 25(4):500–559, 2016.
  27. Ferromagnetic Potts model: Refined #BIS-hardness and related results. SIAM Journal on Computing, 45(6):2004–2065, 2016.
  28. Relaxation times for metastable states in the mean-field model of a ferromagnet. Physical Review, 149(1):301, 1966.
  29. The power of sum-of-squares for detecting hidden structures. In 58th Annual Symposium on Foundations of Computer Science (FOCS 2017), pages 720–731, 2017.
  30. On the integrality gap of degree-4 sum of squares for planted clique. ACM Transactions on Algorithms (TALG), 14(3):1–31, 2018.
  31. Samuel B Hopkins. Statistical inference and the sum of squares method. PhD thesis, Cornell University, 2018.
  32. Efficient Bayesian estimation from few samples: community detection and related problems. In 58th Annual Symposium on Foundations of Computer Science (FOCS 2017), pages 379–390. IEEE, 2017.
  33. Mark Jerrum. Counting, sampling and integrating: algorithms and complexity. Springer Science & Business Media, 2003.
  34. Mean-field approximation, convex hierarchies, and the optimality of correlation rounding: a unified perspective. In 51st Annual ACM SIGACT Symposium on Theory of Computing (STOC 2019), pages 1226–1236, 2019.
  35. Iain M Johnstone. On the distribution of the largest eigenvalue in principal components analysis. Annals of Statistics, pages 295–327, 2001.
  36. A polynomial-time approximation algorithm for the permanent of a matrix with nonnegative entries. Journal of the ACM (JACM), 51(4):671–697, 2004.
  37. Sampling approximately low-rank Ising models: MCMC meets variational methods. In Conference on Learning Theory, pages 4945–4988. PMLR, 2022.
  38. Dmitriy Kunisky. Hypothesis testing with low-degree polynomials in the Morris class of exponential families. In 34th Annual Conference on Learning Theory (COLT 2021), pages 2822–2848. PMLR, 2021.
  39. Is planted coloring easier than planted clique? In 36th Annual Conference on Learning Theory (COLT 2023). PMLR, 2023.
  40. Notes on computational hardness of hypothesis testing: Predictions using the low-degree likelihood ratio. In Paula Cerejeiras and Michael Reissig, editors, Mathematical Analysis, its Applications and Computation, pages 1–50, Cham, 2022. Springer International Publishing.
  41. Online algorithms and lower bounds for average-case matrix discrepancy. arXiv preprint arXiv:2307.10055, 2023.
  42. Michel Ledoux. The concentration of measure phenomenon. Number 89 in Mathematical Surveys & Monographs. American Mathematical Society, 2001.
  43. Glauber dynamics for the mean-field Ising model: cut-off, critical power law, and metastability. Probability Theory and Related Fields, 146:223–265, 2010.
  44. Markov chains and mixing times, volume 107. American Mathematical Soc., 2017.
  45. Elizabeth S Meckes. The random matrix theory of the classical compact groups, volume 218. Cambridge University Press, 2019.
  46. High-temperature expansions and message passing algorithms. Journal of Statistical Mechanics: Theory and Experiment, 2019(11):113301, 2019.
  47. Replica field theory for deterministic models. II. A non-random spin glass with glassy behaviour. Journal of Physics A: Mathematical and General, 27(23):7647, 1994.
  48. Spin glass theory and beyond: an introduction to the replica method and its applications. World Scientific Publishing Company, 1987.
  49. Optimal spectral recovery of a planted vector in a subspace. arXiv preprint arXiv:2105.15081, 2021.
  50. Detection-recovery gap for planted dense cycles. In 36th Annual Conference on Learning Theory (COLT 2023). PMLR, 2023.
  51. Adaptive and self-averaging Thouless-Anderson-Palmer mean-field theory for probabilistic modeling. Physical Review E, 64(5):056131, 2001.
  52. Dmitry Panchenko. The Sherrington-Kirkpatrick model. Springer Science & Business Media, 2013.
  53. Giorgio Parisi. Infinite number of order parameters for spin-glasses. Physical Review Letters, 43(23):1754, 1979.
  54. Giorgio Parisi. A sequence of approximated solutions to the SK model for spin glasses. Journal of Physics A: Mathematical and General, 13(4):L115, 1980.
  55. Mean-field equations for spin models with orthogonal interaction matrices. Journal of Physics A: Mathematical and General, 28(18):5267, 1995.
  56. 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.
  57. Approximate maximum entropy principles via Goemans-Williamson with applications to provable variational methods. Advances in Neural Information Processing Systems, 29, 2016.
  58. Is it easier to count communities than find them? In 14th Innovations in Theoretical Computer Science Conference (ITCS 2023), 2023.
  59. Solvable model of a spin-glass. Physical Review Letters, 35(26):1792, 1975.
  60. Allan Sly. Computational transition at the uniqueness threshold. In 2010 IEEE 51st Annual Symposium on Foundations of Computer Science, pages 287–296. IEEE, 2010.
  61. The computational hardness of counting in two-spin models on d𝑑ditalic_d-regular graphs. In 2012 IEEE 53rd Annual Symposium on Foundations of Computer Science, pages 361–369. IEEE, 2012.
  62. Adaptive simulated annealing: A near-optimal connection between sampling and counting. Journal of the ACM (JACM), 56(3):1–36, 2009.
  63. Computational barriers to estimation from low-degree polynomials. The Annals of Statistics, 50(3):1833–1858, 2022.
  64. Dynamic theory of the spin-glass phase. Physical Review Letters, 47(5):359, 1981.
  65. Michel Talagrand. The Parisi formula. Annals of Mathematics, pages 221–263, 2006.
  66. Alexander S Wein. Optimal low-degree hardness of maximum independent set. Mathematical Statistics and Learning, 4(3):221–251, 2022.
  67. Alexander S Wein. Average-case complexity of tensor decomposition for low-degree polynomials. In Proceedings of the 55th Annual ACM Symposium on Theory of Computing (STOC 2023), pages 1685–1698, 2023.
  68. Lattice-based methods surpass sum-of-squares in clustering. In Conference on Learning Theory, pages 1247–1248. PMLR, 2022.
Citations (7)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now