hep-latNov 8, 2026

Evaluating generative samplers for lattice field theory by scale

Authors: Satoshi Iso, Lingxiao Wang

Organizations: RIKEN Center for Interdisciplinary Theoretical and Mathematical Sciences (iTHEMS), Wako, Saitama 351-0198, Japan · KEK Theory Center, Institute of Particle and Nuclear Studies, KEK, Oho 1-1, Tsukuba, Ibaraki 305-0801, Japan · Institute for Physics of Intelligence, Graduate School of Science, The University of Tokyo, Bunkyo-ku, Tokyo 113-0033, Japan

Abstract

Generative samplers for lattice field theory are commonly evaluated by their effective sample size (ESS). We show that a small global ESS need not imply inaccurate long-distance observables: errors spread over many short-distance modes can dominate this diagnostic. We introduce a scale-resolved diagnostic based on the overlap between coarse-grained model and target distributions. At the lattice cutoff, this overlap determines the asymptotic ESS fraction; lower cutoffs isolate long-wavelength errors. In the exactly solvable free theory, two samplers with comparable ESS yield a 32%32\% bias and no bias in the susceptibility, respectively. In two-dimensional φ4φ^4 theory near criticality, trained diffusion samplers show the same separation of scales: their path-weight ESS fraction falls rapidly over the volumes studied, while low moments of the magnetization remain close to their target values. Varying the reference parameters substantially changes infrared observables, with little effect on the log-weight variance. Given the target magnetization distribution, a marginal Metropolis test maintains an acceptance rate of order one in our tests. Combined with exact local updates, it reduces the remaining mismatch, although residual bias remains at finite relaxation length. In the free field, uniformly bounded relative errors in the proposal mode variances give a volume-independent bound on the number of updates needed for a prescribed accuracy of the chain's stationary mode variances at fixed correlation length. The target marginal must be supplied or computed separately; estimating it from the samplers' own weights can inherit the poor global overlap.

Figures & tables

Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Operator-Guided Model Reduction for Generative Sampling in Lattice Field Theory

    May 11, 2026Moxian QianFlow MatchingMarkov Chain Monte Carlo

  2. Data Free Training of Diffusion Models for Lattice Field Theories

    Oct 13, 2026Dennis Grinwald, Ankur Singha, Khaled Kahouli +2Lattice Field TheoryDiffusion Model Sampling

  3. Sampling the Schwinger Model with Gauge-Equivariant Diffusion

    Jun 25, 2026Octavio Vega, Aida X. El-KhadraDiffusion SamplingGenerative Modeling