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

2026-09-22

AI Summary

本文通过引入块三角联合漂移方法解决了从标准轨迹数据生成一步生成模型的问题，该方法能够直接采样可能的下一个状态，而不需要在时间步之间进行额外的生成步骤。

Abstract

Drifting provides a direct route to one-step generative models, but applying it directly to stochastic transition modeling requires multiple samples of the next state conditioned on the same current state. Standard trajectory data, however, typically provide only one realized next state for each observed current state and therefore do not provide an empirical approximation of the corresponding conditional distribution over possible next states. We introduce block-triangular joint drifting, which instead applies a projected drift field to the empirically accessible joint distribution of consecutive states. Importantly, the block-triangular architecture preserves the current-state marginal while making its second component a direct sampler of the conditional distribution of possible next states. The resulting surrogate generates stochastic trajectories with one model evaluation per time step, without auxiliary generative steps between time steps. Numerical experiments demonstrate accurate marginal and trajectory-dependent statistics and favorable accuracy-cost tradeoffs compared with deterministic, diffusion-, flow-, and distillation-based generative surrogate models.

Problem

• one-step generative models
• stochastic transition modeling
• block-triangular joint drifting
• empirical approximation
• conditional distribution

Innovation

• block-triangular joint drifting
• one-step generative models
• stochastic trajectories
• empirical approximation
• conditional distribution