Autonomous Emergence of Hamiltonian in Deep Generative Models

TL;DR

This paper demonstrates that deep generative models can autonomously discover underlying physical laws, specifically Hamiltonians, in complex many-body systems without explicit physical priors.

Contribution

We introduce an algebraic framework to extract implicit physical interactions from generative models and show they can recover Hamiltonians from equilibrium data.

Findings

The inferred Hamiltonian parameters match ground-truth with 99.7% cosine similarity.

Sparse local parameters explain 87% of the variance in the network's force field.

The framework works on a frustrated 1D O(3) spin glass system.

Abstract

The unprecedented predictive success of deep generative models in complex many-body systems, such as AlphaFold3, raises an epistemological question: do these networks merely memorize data distributions via high-dimensional interpolation, or do they autonomously deduce the underlying physical laws? To address this, we introduce a rigorous algebraic framework to extract the implicit physical interactions learned by generative models. By establishing an exact equivalence between the zero-noise limit of a Riemannian diffusion score field and the thermodynamic restoring force, we utilize the trained neural network as a direct force estimator. Applying this framework to a sequence-dependent, frustrated 1D $O(3)$ spin glass, we probe the latent representations of an $O(3)$-equivariant attention architecture trained solely on thermal equilibrium snapshots. Without incorporating any energetic priors, an overdetermined linear inversion successfully recovers the microscopic Hamiltonian parameters of the spin system. The inferred Hamiltonian parameters exhibit a $99.7\%$ cosine similarity with the ground-truth interaction parameters. Furthermore, these sparse local parameters alone are sufficient to explain $87\%$ of the variance in the continuous force field predicted by the network. Our results provide quantitative, falsifiable evidence that deep generative architectures do not merely perform statistical pattern matching, but autonomously discover and internalize the underlying physical rules.