Consensus in Effective Model Inference for Disordered Ising Systems
Abstract
When independent learners are trained on data from the same disordered system, finite and noisy samples can lead them to different descriptions of the underlying physics. We quantify the reproducibility of such descriptions through consensus, the degree of agreement among independently trained models. In a teacher-student framework on the two-dimensional random-bond Ising model, an ensemble of students each infers a single uniform effective coupling from a finite set of equilibrium configurations drawn from one quenched bond realization. Aggregating the inferred couplings across students and realizations yields the consensus distribution, whose width quantifies the agreement among learners. The variance of this distribution separates exactly into a finite-sampling contribution, bounded below by inverse of Fisher information, and a quenched-disorder contribution. Sum of these two variance is minimized near critical region, so the consensus width has a minimum near the pseudocritical temperature that sharpens with increasing disorder. The two minima arise from different mechanisms: the sampling term inherits the critical peak of the Fisher information, while the disorder term is temperature-independent at leading order and acquires its critical minimum only at fourth order in the disorder strength, through the covariance between the linear and cubic responses to the bond disorder. Because the students fit a uniform coupling to a heterogeneous lattice, the inferred coupling also carries a misspecification bias that survives in the infinite-data limit. This bias displaces the minimum of the mean-squared error above the consensus minimum, so the temperature at which independent learners agree most closely is not the temperature at which their shared answer is most faithful.
Related
- On Zeros and Algorithms for Disordered Systems II: The Antiferromagnetic Ising Model up to Kesten-Stigum
- Fractal signatures of strong universality in the disordered Ising model
- The Disordered Universe 2025: Open Effective Field Theories
- Quantum Ising transition on the Cayley tree: boundary criticality, universality, and an effective Bethe line
- Phase Transitions in Mismatched Bayesian Inference for the Ising Model
BibTeX
@misc{ashraf2026consensus,
title = {{Consensus in Effective Model Inference for Disordered Ising Systems}},
author = {Ashveed Ashraf},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.10731},
eprint = {2609.10731},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.10731},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Consensus in Effective Model Inference for Disordered Ising Systems
AU - Ashveed Ashraf
PY - 2026
DA - 2026/09/09
PB - arXiv
DO - 10.48550/arxiv.2609.10731
UR - https://arxiv.org/abs/2609.10731
AB - When independent learners are trained on data from the same disordered system, finite and noisy samples can lead them to different descriptions of the underlying physics. We quantify the reproducibility of such descriptions through consensus, the degree of agreement among independently trained models. In a teacher-student framework on the two-dimensional random-bond Ising model, an ensemble of students each infers a single uniform effective coupling from a finite set of equilibrium configurations drawn from one quenched bond realization. Aggregating the inferred couplings across students and realizations yields the consensus distribution, whose width quantifies the agreement among learners. The variance of this distribution separates exactly into a finite-sampling contribution, bounded below by inverse of Fisher information, and a quenched-disorder contribution. Sum of these two variance is minimized near critical region, so the consensus width has a minimum near the pseudocritical temperature that sharpens with increasing disorder. The two minima arise from different mechanisms: the sampling term inherits the critical peak of the Fisher information, while the disorder term is temperature-independent at leading order and acquires its critical minimum only at fourth order in the disorder strength, through the covariance between the linear and cubic responses to the bond disorder. Because the students fit a uniform coupling to a heterogeneous lattice, the inferred coupling also carries a misspecification bias that survives in the infinite-data limit. This bias displaces the minimum of the mean-squared error above the consensus minimum, so the temperature at which independent learners agree most closely is not the temperature at which their shared answer is most faithful.
ER -