Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.06702 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916939816763392 |
|---|---|
| author | Bontorno, Ruben Hou, Songyan |
| author_facet | Bontorno, Ruben Hou, Songyan |
| contents | Simulating realistic financial time series is essential for stress testing, scenario generation, and decision-making under uncertainty. Despite advances in deep generative models, there is no consensus metric for their evaluation. We focus on generative AI for financial time series in decision-making applications and employ the nested optimal transport distance, a time-causal variant of optimal transport distance, which is robust to tasks such as hedging, optimal stopping, and reinforcement learning. Moreover, we propose a statistically consistent, naturally parallelizable algorithm for its computation, achieving substantial speedups over existing approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_06702 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Nested Optimal Transport Distances Bontorno, Ruben Hou, Songyan Machine Learning Computational Finance 91G60, 60G07, 65C60 Simulating realistic financial time series is essential for stress testing, scenario generation, and decision-making under uncertainty. Despite advances in deep generative models, there is no consensus metric for their evaluation. We focus on generative AI for financial time series in decision-making applications and employ the nested optimal transport distance, a time-causal variant of optimal transport distance, which is robust to tasks such as hedging, optimal stopping, and reinforcement learning. Moreover, we propose a statistically consistent, naturally parallelizable algorithm for its computation, achieving substantial speedups over existing approaches. |
| title | Nested Optimal Transport Distances |
| topic | Machine Learning Computational Finance 91G60, 60G07, 65C60 |
| url | https://arxiv.org/abs/2509.06702 |