Decision-Focused Forecasting: A Differentiable Multistage Optimisation Architecture

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Peršak, Egon, Anjos, Miguel F.
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