In-context Inverse Optimality for Fair Digital Twins: A Preference-based approach

2025/12/01 by Masti, Daniele, Basciani, Francesco, Fedeli, Arianna +2
#FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Optimization and Control (math.OC) #Software Engineering (cs.SE)

paper · doi:10.48550/arxiv.2512.01650

Abstract

Digital Twins (DTs) are increasingly used as autonomous decision-makers in complex socio-technical systems. Their mathematically optimal decisions often diverge from human expectations, exposing a persistent gap between algorithmic and bounded human rationality. This work addresses this gap by proposing a framework that operationalizes fairness as a learnable objective within optimization-based Digital Twins. We introduce a preference-driven learning pipeline that infers latent fairness objectives directly from human pairwise preferences over feasible decisions. A novel Siamese neural network is developed to generate convex quadratic cost functions conditioned on contextual information. The resulting surrogate objectives align optimization outcomes with human-perceived fairness while maintaining computational efficiency. The approach is demonstrated on a COVID-19 hospital resource allocation scenario. This study provides an actionable path toward embedding human-centered fairness in the design of autonomous decision-making systems.

Citations

• The epistemic dimension of algorithmic fairness: assessing its impact in innovation diffusion and fair policy making
• Optimal Placement of Nature-Based Solutions for Urban Challenges
• From Efficiency to Equity: Measuring Fairness in Preference Learning
• Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms
• Learning Critical Scenarios in Feedback Control Systems for Automated Driving
• Learning Convex Optimization Models
• Deep reinforcement learning from human preferences

Related

• From Efficiency to Equity: Measuring Fairness in Preference Learning
• Fairness With Minimal Harm: A Pareto-Optimal Approach For Healthcare
• Superhuman Fairness
• An Operational Perspective to Fairness Interventions: Where and How to Intervene
• A Tale of Fairness Revisited: Beyond Adversarial Learning for Deep Neural Network Fairness