# Scalable Policy Maximization Under Network Interference

arXiv: https://arxiv.org/abs/2505.18118 · HTML: https://mlsanity.com/paper/2505.18118/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 51 references that are in the map.
- First posted on arXiv 23 May 2025.

## Builds on (most cited first, 12 of 12)

- [Learning to Optimize Via Posterior Sampling](https://mlsanity.com/paper/1301.2609/) (2013)
- [Design and analysis of experiments in networks: Reducing bias from interference](https://mlsanity.com/paper/1404.7530/) (2014)
- [Causal inference for social network data](https://mlsanity.com/paper/1705.08527/) (2017)
- [Experimenting in Equilibrium](https://mlsanity.com/paper/1903.02124/) (2019)
- [Treatment Effects in Market Equilibrium](https://mlsanity.com/paper/2109.11647/) (2021)
- [Elements of estimation theory for causal effects in the presence of network interference](https://mlsanity.com/paper/1702.03578/) (2017)
- [Policy Targeting under Network Interference](https://mlsanity.com/paper/1906.10258/) (2019)
- [Multi-Armed Bandits with Interference](https://mlsanity.com/paper/2402.01845/) (2024)
- [Neighborhood Adaptive Estimators for Causal Inference under Network Interference](https://mlsanity.com/paper/2212.03683/) (2022)
- [Multi-Armed Bandits with Network Interference](https://mlsanity.com/paper/2405.18621/) (2024)
- [Linear Contextual Bandits with Interference](https://mlsanity.com/paper/2409.15682/) (2024)
- [Graph-Dependent Regret Bounds in Multi-Armed Bandits with Interference](https://mlsanity.com/paper/2503.07555/) (2025)

## Built on by (most cited first, 3 of 3)

- [Dynamic Treatment on Networks](https://mlsanity.com/paper/2605.06564/) (2026)
- [Adaptive Policy Learning Under Unknown Network Interference](https://mlsanity.com/paper/2605.11191/) (2026)
- [Learning to target with network interference](https://mlsanity.com/paper/2605.27794/) (2026)

## Abstract (arXiv)

Many interventions, such as vaccines in clinical trials or coupons in online marketplaces, must be assigned sequentially without full knowledge of their effects. Multi-armed bandit algorithms have proven successful in such settings. However, standard independence assumptions fail when the treatment status of one individual impacts the outcomes of others, a phenomenon known as interference. We study optimal-policy learning under interference on a dynamic network. Existing approaches to this problem require repeated observations of the same fixed network and struggle to scale in sample size beyond as few as fifteen connected units -- both limit applications. We show that under common assumptions on the structure of interference, rewards become linear. This enables us to develop a scalable Thompson sampling algorithm that maximizes policy impact when a new n-node network is observed each round. We prove a Bayesian regret bound that is sublinear in n and the number of rounds. Simulation experiments show that our algorithm learns quickly and outperforms existing methods. The results close a key scalability gap between causal inference methods for interference and practical bandit algorithms, enabling policy optimization in large-scale networked systems.