The Nishimori line and Bayesian Statistics

Abstract

``Nishimori line'' is a line or hypersurface in the parameter space of systems with quenched disorder, where simple expressions of the averages of physical quantities over the quenched random variables are obtained. It has been playing an important role in the theoretical studies of the random frustrated systems since its discovery around 1980. In this paper, a novel interpretation of the Nishimori line from the viewpoint of statistical information processing is presented. Our main aim is the reconstruction of the whole theory of the Nishimori line from the viewpoint of Bayesian statistics, or, almost equivalently, from the viewpoint of the theory of error-correcting codes. As a byproduct of our interpretation, counterparts of the Nishimori line in models without gauge invariance are given. We also discussed the issues on the ``finite temperature decoding'' of error-correcting codes in connection with our theme and clarify the role of gauge invariance in this topic.

16 pages, 1 table, no figures, using Iopart.cls and Iopart10.clo, submitted to Journal of Physics A (Mathematical and General), this cond-mat version contains full titles of the references

Cited by in corpus (64)

• Asymptotic analysis of the stochastic block model for modular networks and its algorithmic applications
• Statistical physics of inference: Thresholds and algorithms
• Probabilistic Reconstruction in Compressed Sensing: Algorithms, Phase Diagrams, and Threshold Achieving Matrices
• Scalable detection of statistically significant communities and hierarchies, using message-passing for modularity
• Statistical physics-based reconstruction in compressed sensing
• Detectability thresholds and optimal algorithms for community structure in dynamic networks
• Phase transitions and sample complexity in Bayes-optimal matrix factorization
• The Statistical Physics of Regular Low-Density Parity-Check Error-Correcting Codes
• Mutual Information in Rank-One Matrix Estimation
• Finite-connectivity systems as error-correcting codes
• Networking - A Statistical Physics Perspective
• Statistical Mechanics of Low-Density Parity Check Error-Correcting Codes over Galois Fields
• Strong disorder fixed points in the two-dimensional random-bond Ising model
• Finite-Connectivity Spin-Glass Phase Diagrams and Low Density Parity Check Codes
• Mean-field inference methods for neural networks
• Gallager error correcting codes for binary asymmetric channels
• Transient dynamics for sequence processing neural networks
• Dynamics of the maximum marginal likelihood hyper-parameter estimation in image restoration : gradient descent vs. EM algorithm
• Sampling with flows, diffusion and autoregressive neural networks: A spin-glass perspective
• Optimum estimation via gradients of partition functions and information measures: a statistical-mechanical perspective
• Statistical Physics of Irregular Low-Density Parity-Check Codes
• Unsupervised feature learning from finite data by message passing: discontinuous versus continuous phase transition
• Nishimori meets Bethe: a spectral method for node classification in sparse weighted graphs
• Statistical physics of unsupervised learning with prior knowledge in neural networks
• Algorithmic detectability threshold of the stochastic block model
• Fundamental problems in statistical physics XIV: Lecture on Machine Learning
• Statistical Mechanical Development of a Sparse Bayesian Classifier
• Typical performance of low-density parity-check codes over general symmetric channels
• Retrieving the ground state of spin glasses using thermal noise: Performance of quantum annealing at finite temperatures
• Phase Transitions in Community Detection: A Solvable Toy Model
• Solving Statistical Mechanics on Sparse Graphs with Feedback Set Variational Autoregressive Networks
• Continuous symmetry breaking along the Nishimori line
• Critical Noise Levels for LDPC decoding
• From complex to simple : hierarchical free-energy landscape renormalized in deep neural networks
• Statistical Mechanics Analysis of LDPC Coding in MIMO Gaussian Channels
• Hopfield model with planted patterns: a teacher-student self-supervised learning model
• Statistical Mechanics of Broadcast Channels Using Low Density Parity Check Codes
• Macroscopic Analysis of Vector Approximate Message Passing in a Model Mismatch Setting
• Counting the number of metastable states in the modularity landscape: Algorithmic detectability limit of greedy algorithms in community detection
• Matrix Product Belief Propagation for reweighted stochastic dynamics over graphs
• Dense Hopfield Networks in the Teacher-Student Setting
• Analysis of common attacks in LDPCC-based public-key cryptosystems
• The effect of priors on Learning with Restricted Boltzmann Machines
• Modeling Structured Data Learning with Restricted Boltzmann Machines in the Teacher-Student Setting
• Spatially heterogeneous learning by a deep student machine
• Theoretical characterization of uncertainty in high-dimensional linear classification
• Prediction Errors for Penalized Regressions based on Generalized Approximate Message Passing
• Exact results on high-dimensional linear regression via statistical physics
• Analyticity of the energy in an Ising spin glass with correlated disorder
• Statistical Mechanics of Inference in Epidemic Spreading
• Detectability of Macroscopic Structures in Directed Asymmetric Stochastic Block Model
• Bayesian inference of infected patients in group testing with prevalence estimation
• Statistical mechanics of reputation systems in autonomous networks
• Phase transitions and optimal algorithms for semi-supervised classifications on graphs: from belief propagation to graph convolution network
• The planted XY model: thermodynamics and inference
• Intrinsic regularization effect in Bayesian nonlinear regression scaled by observed data
• Revisiting Nishimori multicriticality through the lens of information measures
• Blind calibration for compressed sensing: State evolution and an online algorithm
• Complex and Non-Complex Phase Structures in Models of Spin Glasses and Information Processing
• The cavity method to protein design problem
• Toward mean-field bound for critical temperature on Nishimori line
• Almost exact recovery in noisy semi-supervised learning
• Dynamical critical behavior on the Nishimori point of frustrated Ising models
• Error Resilience of Fracton Codes and Near Saturation of Code-Capacity Threshold in Three Dimensions