用算子流匹配学习任意域上的随机过程,实现精准函数空间预测。
Stochastic Process Learning via Operator Flow Matching
- 基于算子流匹配构建函数空间的随机过程先验模型
- 可计算任意点集的概率密度,支持新点的均值与密度估计
- 适用于函数回归与先验学习,性能优于现有方法
在神经算子基础上,我们提出一种跨任意域的随机过程学习新框架。具体地,开发了算子流匹配(OFM),用于学习函数空间上的随机过程先验。OFM 能够给出任意点集取值的概率密度,并支持在新点上进行数学上可处理的功能回归,实现均值与密度估计。该方法在随机过程学习、函数回归和先验学习任务中均超越当前最优模型。
原文摘要 · Abstract (English)
Expanding on neural operators, we propose a novel framework for stochastic process learning across arbitrary domains. In particular, we develop operator flow matching (OFM) for learning stochastic process priors on function spaces. OFM provides the probability density of the values of any collection of points and enables mathematically tractable functional regression at new points with mean and density estimation. Our method outperforms state-of-the-art models in stochastic process learning, functional regression, and prior learning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。