Effect of coupling asymmetry on mean-field solutions of the direct and inverse Sherrington–Kirkpatrick model

We study how the degree of symmetry in the couplings influences the performance of three mean-field methods used for solving the direct and inverse problems for generalized Sherrington–Kirkpatrick models. In this context, the direct problem predicts the potentially time-varying magnetizations. The three theories include the first- and second-order Plefka expansions, referred to as naive mean field (nMF) and TAP, respectively, and a mean-field theory which is exact for fully asymmetric couplings. We call the last of these simply MF theory. We show that for the direct problem, nMF performs worse than the other two approximations, TAP outperforms MF when the coupling matrix is nearly symmetric, while MF works better when it is strongly asymmetric. For the inverse problem, MF performs better than both TAP and nMF, although an ad hoc adjustment of TAP can make it comparable to MF. For high temperatures the performance of TAP and MF approach each other.

[1]  S. Leibler,et al.  Neuronal couplings between retinal ganglion cells inferred by efficient inverse statistical physics methods , 2009, Proceedings of the National Academy of Sciences.

[2]  Sompolinsky,et al.  Dynamics of spin systems with randomly asymmetric bonds: Langevin dynamics and a spherical model. , 1987, Physical review. A, General physics.

[3]  Toshiyuki TANAKA.  Mean-field theory of Boltzmann machine learning , 1998 .

[4]  H. Kappen,et al.  Mean field theory for asymmetric neural networks. , 2000, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[5]  Erik Aurell,et al.  Network inference using asynchronously updated kinetic Ising model. , 2010, Physical review. E, Statistical, nonlinear, and soft matter physics.

[6]  T. Hwa,et al.  Identification of direct residue contacts in protein–protein interaction by message passing , 2009, Proceedings of the National Academy of Sciences.

[7]  T. Plefka.  Convergence condition of the TAP equation for the infinite-ranged Ising spin glass model , 1982 .

[8]  Michael J. Berry,et al.  Weak pairwise correlations imply strongly correlated network states in a neural population , 2005, Nature.

[9]  A. Maritan,et al.  Using the principle of entropy maximization to infer genetic interaction networks from gene expression patterns , 2006, Proceedings of the National Academy of Sciences.

[10]  Peter E. Latham,et al.  Pairwise Maximum Entropy Models for Studying Large Biological Systems: When They Can Work and When They Can't , 2008, PLoS Comput. Biol..

[11]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[12]  J. Hertz,et al.  Mean field theory for nonequilibrium network reconstruction. , 2010, Physical review letters.

[13]  E. Aurell,et al.  Dynamics and performance of susceptibility propagation on synthetic data , 2010, 1005.3694.

[14]  A. Bray,et al.  Evidence for massless modes in the 'solvable model' of a spin glass , 1979 .

[15]  Jonathon Shlens,et al.  The Structure of Multi-Neuron Firing Patterns in Primate Retina , 2006, The Journal of Neuroscience.

[16]  Thierry Mora,et al.  Constraint satisfaction problems and neural networks: A statistical physics perspective , 2008, Journal of Physiology-Paris.

[17]  Hilbert J. Kappen,et al.  Efficient Learning in Boltzmann Machines Using Linear Response Theory , 1998, Neural Computation.

[18]  H. Takayama,et al.  TAP free energy structure of SK spin glasses , 1985 .

[19]  Erik Aurell,et al.  Inferring network connectivity using kinetic Ising models , 2010, BMC Neuroscience.