Near-Optimal Dropout-Robust Sortiton

Maya Pal Gambhir, Bailey Flanigan, Aaron Roth
Proceedings of The 29th International Conference on Artificial Intelligence and Statistics, PMLR 300:4357-4365, 2026.

Abstract

Citizens’ assemblies\,–\,small panels of citizens that convene to deliberate on policy issues\,–\,often face the issue of panelists dropping out at the last-minute. Without intervention, these dropouts compromise the size and representativeness of the panel, prompting the question: Without seeing the dropouts ahead of time, can we choose panelists such that \textit{after} dropouts, the panel will be representative and appropriately-sized? We model this problem as a minimax game: the minimizer aims to choose a panel that minimizes the \textit{loss}, i.e., the deviation of the ultimate panel from predefined representation targets. Then, an adversary defines a distribution over dropouts from which the realized dropouts are drawn. Our main contribution is an efficient loss-minimizing algorithm, which remains optimal as we vary the maximizer’s power from worst-case to average case. Our algorithm iteratively plays a projected gradient descent subroutine against an efficient algorithm for computing the best-response dropout distribution. This approach addresses a key open question in the area: how to manage dropouts while ensuring that each potential panelist is chosen with relatively \textit{equal} probabilities. Using real-world datasets, we compare our algorithms to existing benchmarks, and we offer the first characterizations of tradeoffs between robustness, loss, and equality in this problem.

Cite this Paper

BibTeX
@InProceedings{pmlr-v300-gambhir26a, title = { Near-Optimal Dropout-Robust Sortiton }, author = {Gambhir, Maya Pal and Flanigan, Bailey and Roth, Aaron}, booktitle = {Proceedings of The 29th International Conference on Artificial Intelligence and Statistics}, pages = {4357--4365}, 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/gambhir26a/gambhir26a.pdf}, url = {https://proceedings.mlr.press/v300/gambhir26a.html}, abstract = { Citizens’ assemblies\,–\,small panels of citizens that convene to deliberate on policy issues\,–\,often face the issue of panelists dropping out at the last-minute. Without intervention, these dropouts compromise the size and representativeness of the panel, prompting the question: Without seeing the dropouts ahead of time, can we choose panelists such that \textit{after} dropouts, the panel will be representative and appropriately-sized? We model this problem as a minimax game: the minimizer aims to choose a panel that minimizes the \textit{loss}, i.e., the deviation of the ultimate panel from predefined representation targets. Then, an adversary defines a distribution over dropouts from which the realized dropouts are drawn. Our main contribution is an efficient loss-minimizing algorithm, which remains optimal as we vary the maximizer’s power from worst-case to average case. Our algorithm iteratively plays a projected gradient descent subroutine against an efficient algorithm for computing the best-response dropout distribution. This approach addresses a key open question in the area: how to manage dropouts while ensuring that each potential panelist is chosen with relatively \textit{equal} probabilities. Using real-world datasets, we compare our algorithms to existing benchmarks, and we offer the first characterizations of tradeoffs between robustness, loss, and equality in this problem. } }
Endnote
%0 Conference Paper %T Near-Optimal Dropout-Robust Sortiton %A Maya Pal Gambhir %A Bailey Flanigan %A Aaron Roth %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-gambhir26a %I PMLR %P 4357--4365 %U https://proceedings.mlr.press/v300/gambhir26a.html %V 300 %X Citizens’ assemblies\,–\,small panels of citizens that convene to deliberate on policy issues\,–\,often face the issue of panelists dropping out at the last-minute. Without intervention, these dropouts compromise the size and representativeness of the panel, prompting the question: Without seeing the dropouts ahead of time, can we choose panelists such that \textit{after} dropouts, the panel will be representative and appropriately-sized? We model this problem as a minimax game: the minimizer aims to choose a panel that minimizes the \textit{loss}, i.e., the deviation of the ultimate panel from predefined representation targets. Then, an adversary defines a distribution over dropouts from which the realized dropouts are drawn. Our main contribution is an efficient loss-minimizing algorithm, which remains optimal as we vary the maximizer’s power from worst-case to average case. Our algorithm iteratively plays a projected gradient descent subroutine against an efficient algorithm for computing the best-response dropout distribution. This approach addresses a key open question in the area: how to manage dropouts while ensuring that each potential panelist is chosen with relatively \textit{equal} probabilities. Using real-world datasets, we compare our algorithms to existing benchmarks, and we offer the first characterizations of tradeoffs between robustness, loss, and equality in this problem.
APA
Gambhir, M.P., Flanigan, B. & Roth, A.. (2026). Near-Optimal Dropout-Robust Sortiton . Proceedings of The 29th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 300:4357-4365 Available from https://proceedings.mlr.press/v300/gambhir26a.html.

Related Material