# Online Experimental Design With Estimation-Regret Trade-off Under Network Interference

arXiv: https://arxiv.org/abs/2412.03727 · HTML: https://mlsanity.com/paper/2412.03727/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 81 references that are in the map.
- First posted on arXiv 4 Dec 2024.

## Builds on (most cited first, 30 of 36)

- [lil' UCB : An Optimal Exploration Algorithm for Multi-Armed Bandits](https://mlsanity.com/paper/1312.7308/) (2013)
- [Confidence Intervals for Policy Evaluation in Adaptive Experiments](https://mlsanity.com/paper/1911.02768/) (2019)
- [Inference for Batched Bandits](https://mlsanity.com/paper/2002.03217/) (2020)
- [Distributed Exploration in Multi-Armed Bandits](https://mlsanity.com/paper/1311.0800/) (2013)
- [Combinatorial Cascading Bandits](https://mlsanity.com/paper/1507.04208/) (2015)
- [Statistical Inference with M-Estimators on Adaptively Collected Data](https://mlsanity.com/paper/2104.14074/) (2021)
- [Optimal Regret Analysis of Thompson Sampling in Stochastic Multi-armed Bandit Problem with Multiple Plays](https://mlsanity.com/paper/1506.00779/) (2015)
- [Causal Inference under Networked Interference and Intervention Policy Enhancement](https://mlsanity.com/paper/2002.08506/) (2020)
- [Balanced Linear Contextual Bandits](https://mlsanity.com/paper/1812.06227/) (2018)
- [Power Constrained Bandits](https://mlsanity.com/paper/2004.06230/) (2020)
- [Multiple-Play Bandits in the Position-Based Model](https://mlsanity.com/paper/1606.02448/) (2016)
- [A Simple and Provably Efficient Algorithm for Asynchronous Federated Contextual Linear Bandits](https://mlsanity.com/paper/2207.03106/) (2022)
- [Estimation Considerations in Contextual Bandits](https://mlsanity.com/paper/1711.07077/) (2017)
- [Online Multi-Armed Bandits with Adaptive Inference](https://mlsanity.com/paper/2102.13202/) (2021)
- [Combinatorial Bandits with Relative Feedback](https://mlsanity.com/paper/1903.00543/) (2019)
- [A Survey of Online Experiment Design with the Stochastic Multi-Armed Bandit](https://mlsanity.com/paper/1510.00757/) (2015)
- [A framework for Multi-A(rmed)/B(andit) testing with online FDR control](https://mlsanity.com/paper/1706.05378/) (2017)
- [Treatment Effects in Market Equilibrium](https://mlsanity.com/paper/2109.11647/) (2021)
- [Causal inference with misspecified exposure mappings: separating definitions and assumptions](https://mlsanity.com/paper/2103.06471/) (2021)
- [Rate-Optimal Cluster-Randomized Designs for Spatial Interference](https://mlsanity.com/paper/2111.04219/) (2021)
- [Budget-Constrained Multi-Armed Bandits with Multiple Plays](https://mlsanity.com/paper/1711.05928/) (2017)
- [Online Debiasing for Adaptively Collected High-dimensional Data with Applications to Time Series Analysis](https://mlsanity.com/paper/1911.01040/) (2019)
- [Communication Efficient Federated Learning for Generalized Linear Bandits](https://mlsanity.com/paper/2202.01087/) (2022)
- [Causal clustering: design of cluster experiments under network interference](https://mlsanity.com/paper/2310.14983/) (2023)
- [Multi-Armed Bandits with Interference](https://mlsanity.com/paper/2402.01845/) (2024)
- [An Experimental Design for Anytime-Valid Causal Inference on Multi-Armed Bandits](https://mlsanity.com/paper/2311.05794/) (2023)
- [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)
- [Network Cluster-Robust Inference](https://mlsanity.com/paper/2103.01470/) (2021)
- [Adversarial Attacks on Online Learning to Rank with Stochastic Click Models](https://mlsanity.com/paper/2305.19218/) (2023)

## Built on by (most cited first, 9 of 9)

- [Graph-Dependent Regret Bounds in Multi-Armed Bandits with Interference](https://mlsanity.com/paper/2503.07555/) (2025)
- [Balancing Interference and Correlation in Spatial Experimental Designs: A Causal Graph Cut Approach](https://mlsanity.com/paper/2505.20130/) (2025)
- [Design-Based Bandits Under Network Interference: Trade-Off Between Regret and Statistical Inference](https://mlsanity.com/paper/2510.07646/) (2025)
- [Learning Peer Influence Probabilities with Linear Contextual Bandits](https://mlsanity.com/paper/2510.19119/) (2025)
- [Designing Time Series Experiments in A/B Testing with Transformer Reinforcement Learning](https://mlsanity.com/paper/2602.01853/) (2026)
- [From Restless to Contextual: A Thresholding Bandit Reformulation For Finite-horizon Improvement](https://mlsanity.com/paper/2502.05145/) (2025)
- [Beyond ATE: Multi-Criteria Design for A/B Testing](https://mlsanity.com/paper/2509.05864/) (2025)
- [Adaptive Combinatorial Experimental Design: Pareto Optimality for Decision-Making and Inference](https://mlsanity.com/paper/2602.24231/) (2026)
- [Learning to target with network interference](https://mlsanity.com/paper/2605.27794/) (2026)

## Abstract (arXiv)

Network interference has attracted significant attention in the field of causal inference, encapsulating various sociological behaviors where the treatment assigned to one individual within a network may affect the outcomes of others, such as their neighbors. A key challenge in this setting is that standard causal inference methods often assume independent treatment effects among individuals, which may not hold in networked environments. To estimate interference-aware causal effects, a traditional approach is to inherit the independent settings, where practitioners randomly assign experimental participants into different groups and compare their outcomes. While effective in offline settings, this strategy becomes problematic in sequential experiments, where suboptimal decision persists, leading to substantial regret. To address this issue, we introduce a unified interference-aware framework for online experimental design. Compared to existing studies, we extend the definition of arm space by utilizing the statistical concept of exposure mapping, which allows for a more flexible and context-aware representation of treatment effects in networked settings. Crucially, we establish a Pareto-optimal trade-off between estimation accuracy and regret under the network concerning both time period and arm space, which remains superior to baseline models even without network interference. Furthermore, we propose an algorithmic implementation and discuss its generalization across different learning settings and network topology.