NAGO: Noise-Aware Generative Operator via Flow Matching

arXiv:2610.38273 · cs.LG · Submitted 2026-10-28 · Read on arXiv

cs.LG

Submitted: 2026-10-28

Updated: 2026-10-31

Comments: Accepted at NeurIPS 2026. 53 pages including appendices and checklist. Updated to the NeurIPS camera-ready format; research content unchanged. Code: https://github.com/cgymmy/NAGO

License: http://creativecommons.org/licenses/by/4.0/

The gist: We introduce NAGO, a noise-aware generative operator for efficient sampling from invariant measures of stochastic partial differential equations (SPDEs) in function space.

Terminology

Abstract

We introduce NAGO, a noise-aware generative operator for efficient sampling from invariant measures of stochastic partial differential equations (SPDEs) in function space. Our central idea is to treat the source measure as a design variable rather than a fixed Gaussian default. We establish admissibility conditions for well-defined infinite-dimensional flows and show that the finite-band source--target covariance ratio controls the spectral stiffness of the marginal velocity field. This analysis yields an admissibility-constrained spectral-matching rule: choose a source that is sufficiently rough for well-posedness, then minimize covariance mismatch over the resolved Fourier modes. On three representative stochastic-field benchmarks, this source design improves few-step spectral accuracy and several complementary distributional and physical statistics. In a controlled Matern-field ablation, it reduces the accurate RK4 budget from about 30 steps for Gaussian functional flow matching to 3--5 steps, a 6 -- 10 times reduction in neural ODE evaluations. These gains are strongest for stationary multiscale fields and depend on the metric, resolution, and guidance protocol.

Related papers