Central Limit Theorems for Smooth Optimal Transport Maps
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_ | 1866912030841110528 |
|---|---|
| author | Manole, Tudor Balakrishnan, Sivaraman Niles-Weed, Jonathan Wasserman, Larry |
| author_facet | Manole, Tudor Balakrishnan, Sivaraman Niles-Weed, Jonathan Wasserman, Larry |
| contents | One of the central objects in the theory of optimal transport is the Brenier map: the unique monotone transformation which pushes forward an absolutely continuous probability law onto any other given law. A line of recent work has analyzed $L^2$ convergence rates of plugin estimators of Brenier maps, which are defined as the Brenier map between density estimators of the underlying distributions. In this work, we show that such estimators satisfy a pointwise central limit theorem when the underlying laws are supported on the flat torus of dimension $d \geq 3$. We also derive a negative result, showing that these estimators do not converge weakly in $L^2$ when the dimension is sufficiently large. Our proofs hinge upon a quantitative linearization of the Monge-Ampère equation, which may be of independent interest. This result allows us to reduce our problem to that of deriving limit laws for the solution of a uniformly elliptic partial differential equation with a stochastic right-hand side, subject to periodic boundary conditions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_12407 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Central Limit Theorems for Smooth Optimal Transport Maps Manole, Tudor Balakrishnan, Sivaraman Niles-Weed, Jonathan Wasserman, Larry Probability Analysis of PDEs Statistics Theory One of the central objects in the theory of optimal transport is the Brenier map: the unique monotone transformation which pushes forward an absolutely continuous probability law onto any other given law. A line of recent work has analyzed $L^2$ convergence rates of plugin estimators of Brenier maps, which are defined as the Brenier map between density estimators of the underlying distributions. In this work, we show that such estimators satisfy a pointwise central limit theorem when the underlying laws are supported on the flat torus of dimension $d \geq 3$. We also derive a negative result, showing that these estimators do not converge weakly in $L^2$ when the dimension is sufficiently large. Our proofs hinge upon a quantitative linearization of the Monge-Ampère equation, which may be of independent interest. This result allows us to reduce our problem to that of deriving limit laws for the solution of a uniformly elliptic partial differential equation with a stochastic right-hand side, subject to periodic boundary conditions. |
| title | Central Limit Theorems for Smooth Optimal Transport Maps |
| topic | Probability Analysis of PDEs Statistics Theory |
| url | https://arxiv.org/abs/2312.12407 |