Eliciting Truthful Feedback for Preference-Based Learning via the VCG Mechanism

Leo Landolt, Anna Maria Maddux, Andreas Schlaginhaufen, Saurabh Vaishampayan, Maryam Kamgarpour
Proceedings of The 29th International Conference on Artificial Intelligence and Statistics, PMLR 300:5212-5220, 2026.

Abstract

We study resource allocation problems in which a central planner allocates resources among strategic agents with private cost functions in order to minimize a social cost, defined as an aggregate of the agents’ costs. This setting poses two main challenges: (i) the agents’ cost functions may be unknown to them or difficult to specify explicitly, and (ii) agents may misreport their costs strategically. To address these challenges, we propose an algorithm that combines preference-based learning with Vickrey–Clarke–Groves (VCG) payments to incentivize truthful reporting. Our algorithm selects informative preference queries via D-optimal design, estimates cost parameters through maximum likelihood, and computes VCG allocations and payments based on these estimates. In a one-shot setting, we prove that the mechanism is approximately truthful, individually rational, and efficient up to an error of $\tilde{\mathcal O}(K^{-1/2})$ for $K$ preference queries per agent. In an online setting, these guarantees hold asymptotically with sublinear regret at a rate of $\tilde{\mathcal O}(T^{2/3})$ after $T$ rounds. Finally, we validate our approach through a numerical case study on demand response in local electricity markets.

Cite this Paper

BibTeX
@InProceedings{pmlr-v300-landolt26a, title = { Eliciting Truthful Feedback for Preference-Based Learning via the VCG Mechanism }, author = {Landolt, Leo and Maddux, Anna Maria and Schlaginhaufen, Andreas and Vaishampayan, Saurabh and Kamgarpour, Maryam}, booktitle = {Proceedings of The 29th International Conference on Artificial Intelligence and Statistics}, pages = {5212--5220}, year = {2026}, editor = {Khan, Emtiyaz and Li, Yingzhen and Solin, Arno and Ramdas, Aaditya}, volume = {300}, series = {Proceedings of Machine Learning Research}, month = {02--05 May}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v300/main/assets/landolt26a/landolt26a.pdf}, url = {https://proceedings.mlr.press/v300/landolt26a.html}, abstract = { We study resource allocation problems in which a central planner allocates resources among strategic agents with private cost functions in order to minimize a social cost, defined as an aggregate of the agents’ costs. This setting poses two main challenges: (i) the agents’ cost functions may be unknown to them or difficult to specify explicitly, and (ii) agents may misreport their costs strategically. To address these challenges, we propose an algorithm that combines preference-based learning with Vickrey–Clarke–Groves (VCG) payments to incentivize truthful reporting. Our algorithm selects informative preference queries via D-optimal design, estimates cost parameters through maximum likelihood, and computes VCG allocations and payments based on these estimates. In a one-shot setting, we prove that the mechanism is approximately truthful, individually rational, and efficient up to an error of $\tilde{\mathcal O}(K^{-1/2})$ for $K$ preference queries per agent. In an online setting, these guarantees hold asymptotically with sublinear regret at a rate of $\tilde{\mathcal O}(T^{2/3})$ after $T$ rounds. Finally, we validate our approach through a numerical case study on demand response in local electricity markets. } }
Endnote
%0 Conference Paper %T Eliciting Truthful Feedback for Preference-Based Learning via the VCG Mechanism %A Leo Landolt %A Anna Maria Maddux %A Andreas Schlaginhaufen %A Saurabh Vaishampayan %A Maryam Kamgarpour %B Proceedings of The 29th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2026 %E Emtiyaz Khan %E Yingzhen Li %E Arno Solin %E Aaditya Ramdas %F pmlr-v300-landolt26a %I PMLR %P 5212--5220 %U https://proceedings.mlr.press/v300/landolt26a.html %V 300 %X We study resource allocation problems in which a central planner allocates resources among strategic agents with private cost functions in order to minimize a social cost, defined as an aggregate of the agents’ costs. This setting poses two main challenges: (i) the agents’ cost functions may be unknown to them or difficult to specify explicitly, and (ii) agents may misreport their costs strategically. To address these challenges, we propose an algorithm that combines preference-based learning with Vickrey–Clarke–Groves (VCG) payments to incentivize truthful reporting. Our algorithm selects informative preference queries via D-optimal design, estimates cost parameters through maximum likelihood, and computes VCG allocations and payments based on these estimates. In a one-shot setting, we prove that the mechanism is approximately truthful, individually rational, and efficient up to an error of $\tilde{\mathcal O}(K^{-1/2})$ for $K$ preference queries per agent. In an online setting, these guarantees hold asymptotically with sublinear regret at a rate of $\tilde{\mathcal O}(T^{2/3})$ after $T$ rounds. Finally, we validate our approach through a numerical case study on demand response in local electricity markets.
APA
Landolt, L., Maddux, A.M., Schlaginhaufen, A., Vaishampayan, S. & Kamgarpour, M.. (2026). Eliciting Truthful Feedback for Preference-Based Learning via the VCG Mechanism . Proceedings of The 29th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 300:5212-5220 Available from https://proceedings.mlr.press/v300/landolt26a.html.

Related Material