Learning performance in inverse Ising problems with sparse teacher couplings

TL;DR

This paper analyzes the learning performance of pseudolikelihood maximization in inverse Ising problems with sparse teacher couplings, revealing conditions for perfect inference and biases in estimations, supported by theoretical and numerical results.

Contribution

The study provides analytical formulas for learning performance in inverse Ising problems with sparse couplings, extending understanding of inference limits and biases in such models.

Findings

Perfect inference possible when dataset size exceeds twice the number of spins

Estimated couplings tend to be overestimated in magnitude

Theoretical predictions are validated by numerical simulations

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 $N$ as infinity while keeping the dataset size $M$ proportional to $N$, as long as $\alpha=M/N > 2$. 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 Erd\H{o}s--R\'enyi graphs. Numerical simulation results fully support the theoretical predictions. Additional biases in the estimators on loopy graphs are also discussed.