Operator Spectroscopy of Trained Lattice Samplers

TL;DR

This paper introduces an operator-based analysis method for trained lattice samplers, revealing their structure and residual components in various models, and distinguishing different sampler classes through projection onto fixed operator bases.

Contribution

It develops a systematic operator projection framework to analyze trained lattice samplers, uncovering their residual structures and differences across models and classes.

Findings

Zero-mode Binder component is reduced by deflated polynomial P_5(M;t).

Finite-k correlator component is reduced by ^\u221a_{|n|^2=1}.

Projection distinguishes sampler classes and reveals residual structures.

Abstract

Trained lattice samplers are usually judged by the ensembles they generate. Here we instead analyze the trained field-space function itself: a flow-matching velocity, a diffusion score, or a normalizing-flow action residual. We project these functions onto operator bases fixed before the fit, chosen from symmetry, exact Gaussian path limits, finite-volume modes, and gauge covariance. For two-dimensional lattice \(\phi^4\), a trained straight-flow teacher is not described by a local force basis alone. After the local transport basis, the residual separates into a zero-mode Binder component and a lowest-shell finite-\(k\) correlator component. The deflated zero-mode polynomial \(P_5(M;t)\) reduces the dominant Binder-tail component, while \(\phi^\perp_{|n|^2=1}\) reduces the finite-\(k\) correlator component; wrong-parity, off-zero-mode, and random controls do not produce the same reductions. The same projection distinguishes other sampler classes. Diffusion follows the force-resolvent ordering predicted by the free theory, reverse-KL normalizing-flow collapse appears as a forbidden odd zero-mode residual, and gauge-equivariant teachers are resolved by Wilson-loop-force tangent directions. The operator basis is model- and symmetry-dependent, but the test is common: project the trained field-space function and retain sectors that lower held-out residuals and pass the available controls.