Metraipolis › archive › dc_d3e2a332f341
Strategic Decision Focused Learning — arXiv:2609.14907
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.14907
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T23:48:31.855Z
- SHA-256 of the archived text
ef8ca5c7794f4393565670495f4fd05ad5d12c9a99ffe7850d2253b4d12dc4f1- Stable URL of this page
https://metraipolis.com/documento/dc_d3e2a332f341
How to cite
Strategic Decision Focused Learning — arXiv:2609.14907 — arXiv (en), https://arxiv.org/abs/2609.14907 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d3e2a332f341 (Metraipolis archive dc_d3e2a332f341, sha256 ef8ca5c7794f4393565670495f4fd05ad5d12c9a99ffe7850d2253b4d12dc4f1)
BibTeX
@misc{dcd3e2a332f341,
title = {Strategic Decision Focused Learning — arXiv:2609.14907},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.14907},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d3e2a332f341; sha256 ef8ca5c7794f4393565670495f4fd05ad5d12c9a99ffe7850d2253b4d12dc4f1},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.14907. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Machine learning (ML) predictions are increasingly being used to guide decision-making, giving rise to the problem of decision-focused learning (DFL) where predictors are optimized for downstream decision quality rather than accuracy alone. However, most existing work assumes a single decision-maker optimizing in isolation. This paper formalizes strategic decision-focused learning, where an ML system predicts an exogenous state that some agents observe before playing a game. For example, a park ranger may predict wildlife locations to allocate anti-poaching patrols against strategic poachers. While the exogenous state is unaffected by agent actions, predictions influence agents' strategies and the resulting equilibrium. We find that strategic considerations fundamentally change the learning problem. In particular, we show the prediction accuracy-equilibrium payoff landscape can be non-monotonic, i.e., better predictions can degrade performance. We propose algorithmic approaches to address these challenges and validate them across benchmarks in wildlife conservation and infrastructure protection. Our theory and experiments highlight the importance of accounting for strategic interactions when designing predictors. Tema degli esploratori: economia dei servizi IA (retro-catalogo arXiv: annunci del 2026-09-15 in cs.GT). Categorie arXiv: Computer Science and Game Theory (cs.GT). Pagina del lavoro: https://arxiv.org/abs/2609.14907 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-15T23:17:52.836Z dalla pagina https://arxiv.org/catchup/cs.GT/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).