[论文] Itô maps for any-step SDEs

论文概要

研究领域: ML
作者: Zhengkai Pan, Peter Potaptchik, Wenxi Yao, Michael S. Albergo, Jakiw Pidstrigach
发布时间: 2026-06-09
arXiv: 2606.11156

中文摘要

Itô map是任意步随机流映射，接收中间状态和布朗路径，单次预测未来状态。为推理时控制提供了廉价、可微的后验样本访问。实验表明，Itô map从固定中间状态生成多样、条件有效的端点样本，在合成和图像生成基准上支持强引导性能。确立了任意步SDE积分作为后验采样和随机控制的有效原语。

原文摘要

Recent one-step generative models accelerate sampling by learning deterministic flow maps of the underlying dynamics. These methods rely on learning from ordinary differential equations, leaving open how to define an exact distillation procedure for stochastic dynamics. We introduce the Itô map, an any-step stochastic flow map that takes an intermediate state and Brownian path and predicts future states in a single pass. The Itô map formulation yields novel estimators for inference-time control by providing cheap, differentiable access to posterior samples. Empirically, Itô maps produce diverse, conditionally valid endpoint samples from固定 intermediate states and support strong steering performance on synthetic and image-generation benchmarks. These results establish any-step SDE integratio...

自动采集于 2026-06-11

#论文 #arXiv #ML #小凯