Learning performance in inverse Ising problems with sparse teacher couplings
From MaRDI portal
Abstract: We investigate the learning performance of the pseudolikelihood maximization method for inverse Ising problems. In the teacher-student scenario under the assumption that the teacher's couplings are sparse and the student does not know the graphical structure, the learning curve and order parameters are assessed in the typical case using the replica and cavity methods from statistical mechanics. Our formulation is also applicable to a certain class of cost functions having locality; the standard likelihood does not belong to that class. The derived analytical formulas indicate that the perfect inference of the presence/absence of the teacher's couplings is possible in the thermodynamic limit taking the number of spins as infinity while keeping the dataset size proportional to , as long as . Meanwhile, the formulas also show that the estimated coupling values corresponding to the truly existing ones in the teacher tend to be overestimated in the absolute value, manifesting the presence of estimation bias. These results are considered to be exact in the thermodynamic limit on locally tree-like networks, such as the regular random or ErdH{o}s--R'enyi graphs. Numerical simulation results fully support the theoretical predictions. Additional biases in the estimators on loopy graphs are also discussed.
Recommendations
- A statistical physics approach to learning curves for the inverse Ising problem
- Beyond inverse Ising model: structure of the analytical solution
- Simple method for inference in inverse Ising problem using full data
- Statistical mechanics of the inverse Ising problem and the optimal objective function
- Learning of couplings for random asymmetric kinetic Ising models revisited: random correlation matrices and learning curves
Cites work
- A statistical physics approach to learning curves for the inverse Ising problem
- Advanced mean field methods. Theory and practice
- Consistency of Pseudolikelihood Estimation of Fully Visible Boltzmann Machines
- Graphical models, exponential families, and variational inference
- High-dimensional Ising model selection using \(\ell _{1}\)-regularized logistic regression
- scientific article; zbMATH DE number 3513115 (Why is no real title available?)
- Information-Theoretic Limits of Selecting Binary Graphical Models in High Dimensions
- Information, Physics, and Computation
- Learning of couplings for random asymmetric kinetic Ising models revisited: random correlation matrices and learning curves
- Small-correlation expansions for the inverse Ising problem
- Statistical mechanics of the inverse Ising problem and the optimal objective function
- Training Products of Experts by Minimizing Contrastive Divergence
Cited in
(4)- Learning of couplings for random asymmetric kinetic Ising models revisited: random correlation matrices and learning curves
- A statistical physics approach to learning curves for the inverse Ising problem
- Structure learning in inverse Ising problems using ℓ 2-regularized linear estimator
- Ising model selection using ℓ 1-regularized linear regression: a statistical mechanics analysis*
This page was built for publication: Learning performance in inverse Ising problems with sparse teacher couplings
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5854148)
