MGD: Moment Guided Diffusion for Maximum Entropy Generation
This addresses the challenge of efficient and theoretically grounded sample generation for high-dimensional scientific data, though it appears incremental as it hybridizes existing approaches.
The paper tackles the problem of generating samples from limited information by introducing Moment Guided Diffusion (MGD), which combines maximum entropy methods with generative models to avoid slow mixing in high dimensions, achieving convergence to maximum entropy distributions and providing tractable entropy estimates for applications like financial time series and turbulent flows.
Generating samples from limited information is a fundamental problem across scientific domains. Classical maximum entropy methods provide principled uncertainty quantification from moment constraints but require sampling via MCMC or Langevin dynamics, which typically exhibit exponential slowdown in high dimensions. In contrast, generative models based on diffusion and flow matching efficiently transport noise to data but offer limited theoretical guarantees and can overfit when data is scarce. We introduce Moment Guided Diffusion (MGD), which combines elements of both approaches. Building on the stochastic interpolant framework, MGD samples maximum entropy distributions by solving a stochastic differential equation that guides moments toward prescribed values in finite time, thereby avoiding slow mixing in equilibrium-based methods. We formally obtain, in the large-volatility limit, convergence of MGD to the maximum entropy distribution and derive a tractable estimator of the resulting entropy computed directly from the dynamics. Applications to financial time series, turbulent flows, and cosmological fields using wavelet scattering moments yield estimates of negentropy for high-dimensional multiscale processes.