# Online Selection of Diverse Committees

arXiv: https://arxiv.org/abs/2105.09295 · HTML: https://mlsanity.com/paper/2105.09295/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 43 references that are in the map.
- First posted on arXiv 19 May 2021.

## Builds on (most cited first, 11 of 11)

- [Tighter Problem-Dependent Regret Bounds in Reinforcement Learning without Domain Knowledge using Value Function Bounds](https://mlsanity.com/paper/1901.00210/) (2019)
- [Exploration-Exploitation in Constrained MDPs](https://mlsanity.com/paper/2003.02189/) (2020)
- [Linear Contextual Bandits with Knapsacks](https://mlsanity.com/paper/1507.06738/) (2015)
- [Online Convex Optimization in Adversarial Markov Decision Processes](https://mlsanity.com/paper/1905.07773/) (2019)
- [Constrained Upper Confidence Reinforcement Learning](https://mlsanity.com/paper/2001.09377/) (2020)
- [Learning in Markov Decision Processes under Constraints](https://mlsanity.com/paper/2002.12435/) (2020)
- [Multiwinner Elections with Diversity Constraints](https://mlsanity.com/paper/1711.06527/) (2017)
- [Neutralizing Self-Selection Bias in Sampling for Sortition](https://mlsanity.com/paper/2006.10498/) (2020)
- [Multi-Attribute Proportional Representation](https://mlsanity.com/paper/1509.03389/) (2015)
- [A Rule for Committee Selection with Soft Diversity Constraints](https://mlsanity.com/paper/1803.11437/) (2018)
- [The Diverse Cohort Selection Problem](https://mlsanity.com/paper/1709.03441/) (2017)

## Built on by (most cited first, 2 of 2)

- [Online Approval Committee Elections](https://mlsanity.com/paper/2202.06830/) (2022)
- [Multi-Group Proportional Representation in Retrieval](https://mlsanity.com/paper/2407.08571/) (2024)

## Abstract (arXiv)

Citizens' assemblies need to represent subpopulations according to their proportions in the general population. These large committees are often constructed in an online fashion by contacting people, asking for the demographic features of the volunteers, and deciding to include them or not. This raises a trade-off between the number of people contacted (and the incurring cost) and the representativeness of the committee. We study three methods, theoretically and experimentally: a greedy algorithm that includes volunteers as long as proportionality is not violated; a non-adaptive method that includes a volunteer with a probability depending only on their features, assuming that the joint feature distribution in the volunteer pool is known; and a reinforcement learning based approach when this distribution is not known a priori but learnt online.