Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2501.04126 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912641541210112 |
|---|---|
| author | Shi, Yaozhong Ross, Zachary E. Asimaki, Domniki Azizzadenesheli, Kamyar |
| author_facet | Shi, Yaozhong Ross, Zachary E. Asimaki, Domniki Azizzadenesheli, Kamyar |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_04126 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Stochastic Process Learning via Operator Flow Matching Shi, Yaozhong Ross, Zachary E. Asimaki, Domniki Azizzadenesheli, Kamyar Machine Learning 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. |
| title | Stochastic Process Learning via Operator Flow Matching |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2501.04126 |