Decision-Focused Forecasting: A Differentiable Multistage Optimisation Architecture
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916763412725760 |
|---|---|
| author | Peršak, Egon Anjos, Miguel F. |
| author_facet | Peršak, Egon Anjos, Miguel F. |
| contents | Most decision-focused learning work has focused on single stage problems whereas many real-world decision problems are more appropriately modelled using multistage optimisation. In multistage problems contextual information is revealed over time, decisions have to be taken sequentially, and decisions now have an intertemporal effect on future decisions. Decision-focused forecasting is a recurrent differentiable optimisation architecture that expresses a fully differentiable multistage optimisation approach. This architecture enables us to account for the intertemporal decision effects of forecasts. We show what gradient adjustments are made to account for the state-path caused by forecasting. We apply the model to multistage problems in energy storage arbitrage and portfolio optimisation and report that our model outperforms existing approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_14719 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Decision-Focused Forecasting: A Differentiable Multistage Optimisation Architecture Peršak, Egon Anjos, Miguel F. Optimization and Control Artificial Intelligence Machine Learning I.2.8 Most decision-focused learning work has focused on single stage problems whereas many real-world decision problems are more appropriately modelled using multistage optimisation. In multistage problems contextual information is revealed over time, decisions have to be taken sequentially, and decisions now have an intertemporal effect on future decisions. Decision-focused forecasting is a recurrent differentiable optimisation architecture that expresses a fully differentiable multistage optimisation approach. This architecture enables us to account for the intertemporal decision effects of forecasts. We show what gradient adjustments are made to account for the state-path caused by forecasting. We apply the model to multistage problems in energy storage arbitrage and portfolio optimisation and report that our model outperforms existing approaches. |
| title | Decision-Focused Forecasting: A Differentiable Multistage Optimisation Architecture |
| topic | Optimization and Control Artificial Intelligence Machine Learning I.2.8 |
| url | https://arxiv.org/abs/2405.14719 |