# Indirect Active Learning

arXiv: https://arxiv.org/abs/2206.01454 · HTML: https://mlsanity.com/paper/2206.01454/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 60 references that are in the map.
- First posted on arXiv 3 Jun 2022.

## Builds on (most cited first, 8 of 8)

- [Introduction to Multi-Armed Bandits](https://mlsanity.com/paper/1904.07272/) (2019)
- [Kernel Instrumental Variable Regression](https://mlsanity.com/paper/1906.00232/) (2019)
- [Generative Adversarial Active Learning](https://mlsanity.com/paper/1702.07956/) (2017)
- [Rates of Convergence for Nearest Neighbor Classification](https://mlsanity.com/paper/1407.0067/) (2014)
- [Interpretable Sequence Learning for COVID-19 Forecasting](https://mlsanity.com/paper/2008.00646/) (2020)
- [Finite-Sample Analysis of Fixed-k Nearest Neighbor Density Functional Estimators](https://mlsanity.com/paper/1606.01554/) (2016)
- [MEAL: Manifold Embedding-based Active Learning](https://mlsanity.com/paper/2106.11858/) (2021)
- [An Analysis of Active Learning With Uniform Feature Noise](https://mlsanity.com/paper/1505.04215/) (2015)

## Abstract (arXiv)

Traditional models of active learning assume a learner can directly manipulate or query a covariate X in order to study its relationship with a response Y. However, if X is a feature of a complex system, it may be possible only to indirectly influence X by manipulating a control variable Z, a scenario we refer to as Indirect Active Learning. Under a nonparametric model of Indirect Active Learning with a fixed budget, we study minimax convergence rates for estimating the relationship between X and Y locally at a point, obtaining different rates depending on the complexities and noise levels of the relationships between Z and X and between X and Y. We also identify minimax rates for passive learning under comparable assumptions. In many cases, our results show that, while there is an asymptotic benefit to active learning, this benefit is fully realized by a simple two-stage learner that runs two passive experiments in sequence.