Inference algorithm for finite-dimensional spin glasses: belief propagation on the dual lattice.

Starting from a cluster variational method, and inspired by the correctness of the paramagnetic ansatz [at high temperatures in general, and at any temperature in the two-dimensional (2D) Edwards-Anderson (EA) model] we propose a message-passing algorithm--the dual algorithm--to estimate the marginal probabilities of spin glasses on finite-dimensional lattices. We use the EA models in 2D and 3D as benchmarks. The dual algorithm improves the Bethe approximation, and we show that in a wide range of temperatures (compared to the Bethe critical temperature) our algorithm compares very well with Monte Carlo simulations, with the double-loop algorithm, and with exact calculation of the ground state of 2D systems with bimodal and Gaussian interactions. Moreover, it is usually 100 times faster than other provably convergent methods, as the double-loop algorithm. In 2D and 3D the quality of the inference deteriorates only where the correlation length becomes very large, i.e., at low temperatures in 2D and close to the critical temperature in 3D.

[1]  Federico Ricci-Tersenghi,et al.  Replica Cluster Variational Method , 2009, 0906.2695.

[2]  A. Middleton,et al.  Exact algorithm for sampling the two-dimensional Ising spin glass. , 2009, Physical review. E, Statistical, nonlinear, and soft matter physics.

[3]  Guilhem Semerjian,et al.  On the cavity method for decimated random constraint satisfaction problems and the analysis of belief propagation guided decimation algorithms , 2009, ArXiv.

[4]  Andrea Montanari,et al.  Clusters of solutions and replica symmetry breaking in random k-satisfiability , 2008, ArXiv.

[5]  Hilbert J. Kappen,et al.  Sufficient Conditions for Convergence of the Sum–Product Algorithm , 2005, IEEE Transactions on Information Theory.

[6]  H. Katzgraber,et al.  Universality in three-dimensional Ising spin glasses: A Monte Carlo study , 2006, cond-mat/0602212.

[7]  E. Marinari,et al.  Strong universality and algebraic scaling in two-dimensional Ising spin glasses. , 2006, Physical review letters.

[8]  William T. Freeman,et al.  Constructing free-energy approximations and generalized belief propagation algorithms , 2005, IEEE Transactions on Information Theory.

[9]  Y. Kabashima.  Replicated Bethe Free Energy: A Variational Principle behind Survey Propagation , 2005, cond-mat/0506311.

[10]  F. Krzakala,et al.  Spin glass models with ferromagnetically biased couplings on the Bethe lattice: analytic solutions and numerical simulations , 2004, cond-mat/0403053.

[11]  A. Pagnani,et al.  Near-optimal configurations in mean-field disordered systems. , 2003, Physical review. E, Statistical, nonlinear, and soft matter physics.

[12]  Y. Kabashima.  Propagating beliefs in spin-glass models , 2002, cond-mat/0211500.

[13]  Riccardo Zecchina,et al.  Coloring random graphs , 2002, Physical review letters.

[14]  M. Mézard,et al.  Random K-satisfiability problem: from an analytic solution to an efficient algorithm. , 2002, Physical review. E, Statistical, nonlinear, and soft matter physics.

[15]  M. Mézard,et al.  The Cavity Method at Zero Temperature , 2002, cond-mat/0207121.

[16]  Alan L. Yuille,et al.  CCCP Algorithms to Minimize the Bethe and Kikuchi Free Energies: Convergent Alternatives to Belief Propagation , 2002, Neural Computation.

[17]  V. Akila,et al.  Information , 2001, The Lancet.

[18]  M. Mézard,et al.  The Bethe lattice spin glass revisited , 2000, cond-mat/0009418.

[19]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[20]  L. Goddard.  Information Theory , 1962, Nature.

[21]  R. Kikuchi.  A Theory of Cooperative Phenomena , 1951 .