# Learning treatment effects while treating those in need

arXiv: https://arxiv.org/abs/2407.07596 · HTML: https://mlsanity.com/paper/2407.07596/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 42 references that are in the map.
- First posted on arXiv 10 Jul 2024.

## Builds on (most cited first, 14 of 14)

- [Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits](https://mlsanity.com/paper/1402.0555/) (2014)
- [Beyond UCB: Optimal and Efficient Contextual Bandits with Regression Oracles](https://mlsanity.com/paper/2002.04926/) (2020)
- [Online Learning under Delayed Feedback](https://mlsanity.com/paper/1306.0686/) (2013)
- [Balanced Linear Contextual Bandits](https://mlsanity.com/paper/1812.06227/) (2018)
- [Nonparametric causal effects based on incremental propensity score interventions](https://mlsanity.com/paper/1704.00211/) (2017)
- [Semi-Parametric Efficient Policy Learning with Continuous Actions](https://mlsanity.com/paper/1905.10116/) (2019)
- [Balancing Competing Objectives with Noisy Data: Score-Based Classifiers for Welfare-Aware Machine Learning](https://mlsanity.com/paper/2003.06740/) (2020)
- [Clip-OGD: An Experimental Design for Adaptive Neyman Allocation in Sequential Experiments](https://mlsanity.com/paper/2305.17187/) (2023)
- [The Relative Value of Prediction in Algorithmic Decision Making](https://mlsanity.com/paper/2312.08511/) (2023)
- [Adaptive Neyman Allocation](https://mlsanity.com/paper/2309.08808/) (2023)
- [Machine Learning Who to Nudge: Causal vs Predictive Targeting in a Field Experiment on Student Financial Aid Renewal](https://mlsanity.com/paper/2310.08672/) (2023)
- [Scarce Resource Allocations That Rely On Machine Learning Should Be Randomized](https://mlsanity.com/paper/2404.08592/) (2024)
- [Integrating Reward Maximization and Population Estimation: Sequential Decision-Making for Internal Revenue Service Audit Selection](https://mlsanity.com/paper/2204.11910/) (2022)
- [Optimizing the tie-breaker regression discontinuity design](https://mlsanity.com/paper/1808.07563/) (2018)

## Built on by (most cited first, 8 of 8)

- [The Value of Prediction in Identifying the Worst-Off](https://mlsanity.com/paper/2501.19334/) (2025)
- [Comparing Targeting Strategies for Maximizing Social Welfare with Limited Resources](https://mlsanity.com/paper/2411.07414/) (2024)
- [Good Allocations from Bad Estimates](https://mlsanity.com/paper/2601.05597/) (2026)
- [The Hidden Cost of Waiting for Accurate Predictions](https://mlsanity.com/paper/2503.00650/) (2025)
- [Dependent Randomized Rounding for Budget Constrained Experimental Design](https://mlsanity.com/paper/2506.12677/) (2025)
- [Performative Learning Theory](https://mlsanity.com/paper/2602.04402/) (2026)
- [Deployment of AI-Assisted Interventions: Capacity Constraints and Noisy Compliance](https://mlsanity.com/paper/2604.14370/) (2026)
- [Learning Treatment Effects during Resource Allocation via Priority-Queue Randomization](https://mlsanity.com/paper/2605.25169/) (2026)

## Abstract (arXiv)

Many social programs attempt to allocate scarce resources to people with the greatest need. Indeed, public services increasingly use algorithmic risk assessments motivated by this goal. However, targeting the highest-need recipients often conflicts with attempting to evaluate the causal effect of the program as a whole, as the best evaluations would be obtained by randomizing the allocation. We propose a framework to design randomized allocation rules which optimally balance targeting high-need individuals with learning treatment effects, presenting policymakers with a Pareto frontier between the two goals. We give sample complexity guarantees for the policy learning problem and provide a computationally efficient strategy to implement it. We then collaborate with the human services department of Allegheny County, Pennsylvania to evaluate our methods on data from real service delivery settings. Optimized policies can substantially mitigate the tradeoff between learning and targeting. For example, it is often possible to obtain 90% of the optimal utility in targeting high-need individuals while ensuring that the average treatment effect can be estimated with less than 2 times the samples that a randomized controlled trial would require. Mechanisms for targeting public services often focus on measuring need as accurately as possible. However, our results suggest that algorithmic systems in public services can be most impactful if they incorporate program evaluation as an explicit goal alongside targeting.