On the Inverse Flow Matching Problem in the One-Dimensional and Gaussian Cases
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914223468052480 |
|---|---|
| author | Korotin, Alexander Pammer, Gudmund |
| author_facet | Korotin, Alexander Pammer, Gudmund |
| contents | This paper studies the inverse problem of flow matching (FM) between distributions with finite exponential moment, a problem motivated by modern generative AI applications such as the distillation of flow matching models. Uniqueness of the solution is established in two cases - the one-dimensional setting and the Gaussian case. The general multidimensional problem remains open for future studies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_23265 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | On the Inverse Flow Matching Problem in the One-Dimensional and Gaussian Cases Korotin, Alexander Pammer, Gudmund Machine Learning This paper studies the inverse problem of flow matching (FM) between distributions with finite exponential moment, a problem motivated by modern generative AI applications such as the distillation of flow matching models. Uniqueness of the solution is established in two cases - the one-dimensional setting and the Gaussian case. The general multidimensional problem remains open for future studies. |
| title | On the Inverse Flow Matching Problem in the One-Dimensional and Gaussian Cases |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2512.23265 |