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

arXiv: https://arxiv.org/abs/2512.01650 · HTML: https://mlsanity.com/paper/2512.01650/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 23 references that are in the map.
- First posted on arXiv 1 Dec 2025.

## Builds on (most cited first, 9 of 9)

- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms](https://mlsanity.com/paper/2406.02900/) (2024)
- [Learning Convex Optimization Models](https://mlsanity.com/paper/2006.04248/) (2020)
- [GLISp-r: A preference-based optimization algorithm with convergence guarantees](https://mlsanity.com/paper/2202.01125/) (2022)
- [Formulation, existence, and computation of boundedly rational dynamic user equilibrium with fixed or endogenous user tolerance](https://mlsanity.com/paper/1402.1211/) (2014)
- [From Efficiency to Equity: Measuring Fairness in Preference Learning](https://mlsanity.com/paper/2410.18841/) (2024)
- [Learning Critical Scenarios in Feedback Control Systems for Automated Driving](https://mlsanity.com/paper/2209.12586/) (2022)
- [Optimal Placement of Nature-Based Solutions for Urban Challenges](https://mlsanity.com/paper/2502.11065/) (2025)
- [The epistemic dimension of algorithmic fairness: assessing its impact in innovation diffusion and fair policy making](https://mlsanity.com/paper/2504.02856/) (2025)

## Abstract (arXiv)

Digital Twins (DTs) are increasingly used as autonomous decision-makers in complex socio-technical systems. However, their mathematically optimal decisions often diverge from human expectations, revealing a persistent mismatch between algorithmic and bounded human rationality. This work addresses this challenge by proposing a framework that introduces fairness as a learnable objective within optimization-based Digital Twins. In this respect, a preference-driven learning workflow that infers latent fairness objectives directly from human pairwise preferences over feasible decisions is introduced. A dedicated Siamese neural network is developed to generate convex quadratic cost functions conditioned on contextual information. The resulting surrogate objectives drive the optimization procedure toward solutions that better reflect human-perceived fairness while maintaining computational efficiency. The effectiveness of the approach is demonstrated on a COVID-19 hospital resource allocation scenario. Overall, this work offers a practical solution to integrate human-centered fairness into the design of autonomous decision-making systems.