# Good Allocations from Bad Estimates

arXiv: https://arxiv.org/abs/2601.05597 · HTML: https://mlsanity.com/paper/2601.05597/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 49 references that are in the map.
- First posted on arXiv 9 Jan 2026.

## Builds on (most cited first, 21 of 21)

- [Meta-learners for Estimating Heterogeneous Treatment Effects using Machine Learning](https://mlsanity.com/paper/1706.03461/) (2017)
- [Quasi-Oracle Estimation of Heterogeneous Treatment Effects](https://mlsanity.com/paper/1712.04912/) (2017)
- [Generalized Random Forests](https://mlsanity.com/paper/1610.01271/) (2016)
- [On the Complexity of Best Arm Identification in Multi-Armed Bandit Models](https://mlsanity.com/paper/1407.4443/) (2014)
- [Recursive Partitioning for Heterogeneous Causal Effects](https://mlsanity.com/paper/1504.01132/) (2015)
- [Batch Policy Learning under Constraints](https://mlsanity.com/paper/1903.08738/) (2019)
- [Balanced Policy Evaluation and Learning](https://mlsanity.com/paper/1705.07384/) (2017)
- [The True Sample Complexity of Identifying Good Arms](https://mlsanity.com/paper/1906.06594/) (2019)
- [Difficult Lessons on Social Prediction from Wisconsin Public Schools](https://mlsanity.com/paper/2304.06205/) (2023)
- [Nearly Instance Optimal Sample Complexity Bounds for Top-k Arm Selection](https://mlsanity.com/paper/1702.03605/) (2017)
- [Top-k Combinatorial Bandits with Full-Bandit Feedback](https://mlsanity.com/paper/1905.12624/) (2019)
- [Interventions over Predictions: Reframing the Ethical Debate for Actuarial Risk Assessment](https://mlsanity.com/paper/1712.08238/) (2017)
- [PAC Identification of Many Good Arms in Stochastic Multi-Armed Bandits](https://mlsanity.com/paper/1901.08386/) (2019)
- [The Relative Value of Prediction in Algorithmic Decision Making](https://mlsanity.com/paper/2312.08511/) (2023)
- [Allocation Requires Prediction Only if Inequality Is Low](https://mlsanity.com/paper/2406.13882/) (2024)
- [Learning treatment effects while treating those in need](https://mlsanity.com/paper/2407.07596/) (2024)
- [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)
- [Who Pays the RENT? Implications of Spatial Inequality for Prediction-Based Allocation Policies](https://mlsanity.com/paper/2508.08573/) (2025)
- [Data-driven Design of Randomized Control Trials with Guaranteed Treatment Effects](https://mlsanity.com/paper/2410.11212/) (2024)
- [The Hidden Cost of Waiting for Accurate Predictions](https://mlsanity.com/paper/2503.00650/) (2025)

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

- [Mitigating Hallucinations in Large Vision-Language Models via Causal Route Gating](https://mlsanity.com/paper/2605.24024/) (2026)
- [On the Meta-Design of Allocation Problems](https://mlsanity.com/paper/2602.08786/) (2026)

## Abstract (arXiv)

Conditional average treatment effect (CATE) estimation is the de facto gold standard for targeting a treatment to a heterogeneous population. The method estimates treatment effects up to an error ε > 0 in each of M different strata of the population, targeting individuals in decreasing order of estimated treatment effect until the budget runs out. In general, this method requires O(M/ε2) samples. This is best possible if the goal is to estimate all treatment effects up to an ε error. In this work, we show how to achieve the same total treatment effect as CATE with only O(M/ε) samples for natural distributions of treatment effects. The key insight is that coarse estimates suffice for near-optimal treatment allocations. In addition, we show that budget flexibility can further reduce the sample complexity of allocation. Finally, we evaluate our algorithm on various real-world RCT datasets. In all cases, it finds nearly optimal treatment allocations with surprisingly few samples. Our work highlights the fundamental distinction between treatment effect estimation and treatment allocation: the latter requires far fewer samples.