Generative diffusion surrogates with analytical variance schedule
In the authors' words
Abstract Stochastic transport describes physical systems in which an initially structured distribution spreads under unresolved forcing, scattering, or heterogeneous media. Useful surrogates for such systems should be probabilistic, time-resolved, and able to represent non-Gaussian distributional structure. Generative diffusion models, which corrupt data with Gaussian noise and learn a reverse flow back to structured states, have these properties. Their noise schedules, however, are usually chosen heuristically: image and audio generation—the canonical use cases—provide no physical clock. In transport, by contrast, the variance, or mean-square displacement, is often known from macroscopic theory or empirical scaling even when the full distribution is not. Here we prescribe the forward noising rate as the time derivative of this variance, turning generative time into a calibrated transport clock. The variance path is enforced by construction, while the learned score field represents how non-Gaussian structure inherited from entrance data is smoothed along that path, requiring no intermediate-time physical transport data. For ballistic-to-diffusive transport in turbulent plasmas, the surrogate matches test-particle distributions, reproduces the laboratory-measured variance scale, and tracks the simulated kurtosis evolution without schedule tuning, enabling calibrated emulation and likelihood-based inference.
In plain words AI summary
Stochastic transport describes how structured distributions spread due to random forces or complex environments. Usually their noise schedules are chosen by trial and error, but here the authors set the noising rate using known variance from physical theory. This approach needs no intermediate-time physical data to learn how non-Gaussian structure smooths over time. For turbulent plasma transport, the surrogate matches particle distributions, reproduces measured variance, and tracks kurtosis evolution without tuning.
Written by Kimi K2.5 using only the abstract above. Jev checked that every sentence is supported by the abstract sentences it cites, and removed any that were not. Point at a sentence to highlight its source. 1 sentence was removed for not being supported by the abstract.
Appeared: Saturday, October 10. Nature Communications. Peer-reviewed journal.