Tractable approximations for probabilistic models: The adaptive TAP mean field approach
arXiv:cond-mat/0102274 · doi:10.1103/PhysRevLett.86.3695
Abstract
We develop an advanced mean field method for approximating averages in probabilistic data models that is based on the TAP approach of disorder physics. In contrast to conventional TAP, where the knowledge of the distribution of couplings between the random variables is required, our method adapts to the concrete couplings. We demonstrate the validity of our approach, which is sofar restricted to models with non-glassy behaviour, by replica calculations for a wide class of models as well as by simulations for a real data set.
arXiv comment5 Pages, 2 figures, accepted for publication in Phys. Rev. Lett
References in corpus (1)
Cited by in corpus (28)
- Statistical physics of inference: Thresholds and algorithms
- Optimal Errors and Phase Transitions in High-Dimensional Generalized Linear Models
- Inference from correlated patterns: a unified theory for perceptron learning and linear vector channels
- High-temperature Expansions and Message Passing Algorithms
- Mean-field inference methods for neural networks
- Perceptron capacity revisited: classification ability for correlated patterns
- Perturbative construction of mean-field equations in extensive-rank matrix factorization and denoising
- Susceptibility Propagation by Using Diagonal Consistency
- A Deterministic and Generalized Framework for Unsupervised Learning with Restricted Boltzmann Machines
- A mean field method with correlations determined by linear response
- Adaptive Thouless-Anderson-Palmer approach to inverse Ising problems with quenched random fields
- A statistical mechanics approach to de-biasing and uncertainty estimation in LASSO for random measurements
- Statistical mechanical analysis of the Kronecker channel model for MIMO wireless communication
- Statistical mechanical analysis of the linear vector channel in digital communication
- Macroscopic Analysis of Vector Approximate Message Passing in a Model Mismatch Setting
- Belief Propagation Algorithm for Portfolio Optimization Problems
- Cross validation in sparse linear regression with piecewise continuous nonconvex penalties and its acceleration
- Optimal Learning with Excitatory and Inhibitory synapses
- Local convexity of the TAP free energy and AMP convergence for Z2-synchronization
- Ising distribution as a latent variable model
- Semi-analytic approximate stability selection for correlated data in generalized linear models
- Universal Behavior in Large-scale Aggregation of Independent Noisy Observations
- Perturbative Interpretation of Adaptive Thouless-Anderson-Palmer Free Energy
- Blind calibration for compressed sensing: State evolution and an online algorithm
- Improving variational methods via pairwise linear response identities
- Variational Gaussian Approximation in Replica Analysis of Parametric Models
- Accelerating Cross-Validation in Multinomial Logistic Regression with -Regularization
- Investigating maximum likelihood based training of infinite mixtures for uncertainty quantification