A new architecture of high-order deep neural networks that learn martingales
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_ | 1866908394037706752 |
|---|---|
| author | Ninomiya, Syoiti Ma, Yuming |
| author_facet | Ninomiya, Syoiti Ma, Yuming |
| contents | A new deep-learning neural network architecture based on high-order weak approximation algorithms for stochastic differential equations (SDEs) is proposed. The architecture enables the efficient learning of martingales by deep learning models. The behaviour of deep neural networks based on this architecture, when applied to the problem of pricing financial derivatives, is also examined. The core of this new architecture lies in the high-order weak approximation algorithms of the explicit Runge--Kutta type, wherein the approximation is realised solely through iterative compositions and linear combinations of vector fields of the target SDEs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_03789 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A new architecture of high-order deep neural networks that learn martingales Ninomiya, Syoiti Ma, Yuming Machine Learning Probability Computational Finance 65C30, 60H35, 91G60, 68T07 A new deep-learning neural network architecture based on high-order weak approximation algorithms for stochastic differential equations (SDEs) is proposed. The architecture enables the efficient learning of martingales by deep learning models. The behaviour of deep neural networks based on this architecture, when applied to the problem of pricing financial derivatives, is also examined. The core of this new architecture lies in the high-order weak approximation algorithms of the explicit Runge--Kutta type, wherein the approximation is realised solely through iterative compositions and linear combinations of vector fields of the target SDEs. |
| title | A new architecture of high-order deep neural networks that learn martingales |
| topic | Machine Learning Probability Computational Finance 65C30, 60H35, 91G60, 68T07 |
| url | https://arxiv.org/abs/2505.03789 |