One-Step Generative Surrogate Models via Block-Triangular Joint Drifting

DOI10.48550/arXiv.2609.26435MaRDI QIDQ7353482arXivFDO

Authors Benjamin Peherstorfer, Nicholas Geissler, Shreya Jha, Ricardo Baptista

Publication date 22 September 2026

Tldr We introduce block-triangular joint drifting to generate stochastic trajectories from standard trajectory data with one model evaluation per time step without auxiliary generative steps between time steps. By applying a projected drift field to the empirically accessible joint distribution of consecutive states, we preserve the current-state marginal while making its second component a direct sampler of the conditional distribution of possible next states.

Full work available at URL https://doi.org/10.48550/arXiv.2609.26435

arXiv classification

cs.LG math.NA

Cites work

A comprehensive deep learning-based approach to reduced order modeling of nonlinear time-dependent parametrized PDEs
A nine-dimensional Lorenz system to study high-dimensional chaos
A user's guide to optimal transport
Conditional sampling with monotone GANs: from generative models to likelihood-free inference
Coupling techniques for nonlinear ensemble filtering
Data-driven operator inference for nonintrusive projection-based model reduction
Generative forecasting with joint probability models
Inference via low-dimensional couplings
Interpolating between Optimal Transport and MMD using Sinkhorn Divergences
Kernel methods are competitive for operator learning
Learning stochastic dynamical systems with neural networks mimicking the Euler-Maruyama scheme
Learning Stochastic Reduced Models from Data: A Nonintrusive Approach
On the representation and learning of monotone triangular transport maps
Stochastic Interpolants: A Unifying Framework for Flows and Diffusions

This page was built for publication: One-Step Generative Surrogate Models via Block-Triangular Joint Drifting

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7353482)