Conditional Optimal Transport on Function Spaces
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910319349071872 |
|---|---|
| author | Hosseini, Bamdad Hsu, Alexander W. Taghvaei, Amirhossein |
| author_facet | Hosseini, Bamdad Hsu, Alexander W. Taghvaei, Amirhossein |
| contents | We present a systematic study of conditional triangular transport maps in function spaces from the perspective of optimal transportation and with a view towards amortized Bayesian inference. More specifically, we develop a theory of constrained optimal transport problems that describe block-triangular Monge maps that characterize conditional measures along with their Kantorovich relaxations. This generalizes the theory of optimal triangular transport to separable infinite-dimensional function spaces with general cost functions. We further tailor our results to the case of Bayesian inference problems and obtain regularity estimates on the conditioning maps from the prior to the posterior. Finally, we present numerical experiments that demonstrate the computational applicability of our theoretical results for amortized and likelihood-free inference of functional parameters. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_05672 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Conditional Optimal Transport on Function Spaces Hosseini, Bamdad Hsu, Alexander W. Taghvaei, Amirhossein Optimization and Control Probability Computation Machine Learning 49Q22, 62G86, 62F15, 60B05 We present a systematic study of conditional triangular transport maps in function spaces from the perspective of optimal transportation and with a view towards amortized Bayesian inference. More specifically, we develop a theory of constrained optimal transport problems that describe block-triangular Monge maps that characterize conditional measures along with their Kantorovich relaxations. This generalizes the theory of optimal triangular transport to separable infinite-dimensional function spaces with general cost functions. We further tailor our results to the case of Bayesian inference problems and obtain regularity estimates on the conditioning maps from the prior to the posterior. Finally, we present numerical experiments that demonstrate the computational applicability of our theoretical results for amortized and likelihood-free inference of functional parameters. |
| title | Conditional Optimal Transport on Function Spaces |
| topic | Optimization and Control Probability Computation Machine Learning 49Q22, 62G86, 62F15, 60B05 |
| url | https://arxiv.org/abs/2311.05672 |