Preprint

Strategic Decision Focused Learning

Tinashe Handina Yu-Cun Diao Adam Wierman Eric Mazumdar

Sep 2026 · 0 citations · 35 references

Computer Science

TL;DR

This paper formalizes strategic decision-focused learning, where an ML system predicts an exogenous state that some agents observe before playing a game, and shows the prediction accuracy-equilibrium payoff landscape can be non-monotonic, i.e., better predictions can degrade performance.

Abstract

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.

arXiv Semantic Scholar

View source

Similar papers

#machine learning Preprint Sep 2026

RL-PaO: Prediction as Action in Decision Making under Uncertainty

Decision-making under uncertainty often relies on predicted parameters, yet accurate prediction does not necessarily lead to good operational decisions. Aligning prediction with downstream optimization requires learning from the consequences of the decisions those predictions induce. We introduce RL-PaO, a reinforcemen...

Jia-Hui Feng, Da-Fang Zhao, Zheng Chen et al. · 0 citations

Preprint Aug 2026

Integrated Learning and Robust Optimization

This work proposes an integrated learning and robust optimization (ILRO) framework, where a robust decision problem is used both to define the training problem (termed the RSPO loss problem), and to produce the deployed decision, which achieves both robustness and learning-decision alignment.

Chengpeng Tan, Yuchen Mao, Shu-Ming Wang et al. · 0 citations

Open access Aug 2026

Decision-Driven Regularization: A Blended Model for Learning and Optimization

This paper proposes a biobjective formulation that balances prediction accuracy and cost minimization, termed decision-driven regularization, which is shown to be numerically superior to other benchmarks, such as ordinary least squares, random forest, XGBoost, SPO+, perturbation gradient, and learning and rank, in the...

G. Loke, Qin-Shen Tang, Yangge Xiao et al. · INFORMS journal on computing · 1 citation

#machine learning Preprint Sep 2026

Reinforcement learning to choose optimizers

No single optimization method is uniformly best for all problems, and the most suitable optimizer choice can change during a run. Existing approaches that change optimizer during execution typically predetermine part of the strategy: the portfolio is restricted to one algorithm class, the switch occurs once at a fixed...

Martin P van der Schelling, D. Toshniwal, M. A. Bessa · 0 citations

Preprint Aug 2026

An inverse mixed-integer optimization framework for learning interpretable models of expert decision making

This work develops an inverse optimization approach to jointly learn the decision-maker's preferences and the decision rules governing their choices, which leads to better predictions and greater flexibility in capturing and replicating expert decision making.

Anurag Holani, Rishabh Gupta, J. Wassick et al. · 1 citation

#machine learning Preprint Sep 2026

Decision-Focused Learning for Mean-Variance Portfolio Optimization via KKT-Based Reformulation

Mean-variance portfolio optimization (MVO) is a central framework in data-driven asset management. A widely adopted approach is a two-stage framework that first predicts expected returns and then solves the optimization problem based on these predictions, with the predictive models trained by minimizing prediction erro...

Kensei Nosaka, Shunnosuke Ikeda, Yuichi Takano · 0 citations