# Double Debiased Machine Learning for Mediation Analysis with Continuous Treatments

arXiv: https://arxiv.org/abs/2503.06156 · HTML: https://mlsanity.com/paper/2503.06156/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 75 references that are in the map.
- First posted on arXiv 8 Mar 2025.

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

- [Direct and Indirect Effects](https://mlsanity.com/paper/1301.2300/) (2013)
- [Semiparametric doubly robust targeted double machine learning: a review](https://mlsanity.com/paper/2203.06469/) (2022)
- [Nonparametric methods for doubly robust estimation of continuous treatment effects](https://mlsanity.com/paper/1507.00747/) (2015)
- [A general framework for inference on algorithm-agnostic variable importance](https://mlsanity.com/paper/2004.03683/) (2020)
- [The Influence Function of Semiparametric Estimators](https://mlsanity.com/paper/1508.01378/) (2015)
- [De-Biased Machine Learning of Global and Local Parameters Using Regularized Riesz Representers](https://mlsanity.com/paper/1802.08667/) (2018)
- [Fast convergence rates for dose-response estimation](https://mlsanity.com/paper/2207.11825/) (2022)
- [Sequential Kernel Embedding for Mediated and Time-Varying Dose Response Curves](https://mlsanity.com/paper/2111.03950/) (2021)
- [Debiased inference for a covariate-adjusted regression function](https://mlsanity.com/paper/2210.06448/) (2022)
- [Multiply Robust Causal Mediation Analysis with Continuous Treatments](https://mlsanity.com/paper/2105.09254/) (2021)
- [Counterfactual Learning of Stochastic Policies with Continuous Actions](https://mlsanity.com/paper/2004.11722/) (2020)
- [A nonparametric doubly robust test for a continuous treatment effect](https://mlsanity.com/paper/2202.03369/) (2022)

## Built on by (most cited first, 1 of 1)

- [Kernel Treatment Effects with Adaptively Collected Data](https://mlsanity.com/paper/2510.10245/) (2025)

## Abstract (arXiv)

Uncovering causal mediation effects is of significant value to practitioners seeking to isolate the direct treatment effect from the potential mediated effect. We propose a double machine learning (DML) algorithm for mediation analysis that supports continuous treatments. To estimate the target mediated response curve, our method uses a kernel-based doubly robust moment function for which we prove asymptotic Neyman orthogonality. This allows us to obtain asymptotic normality with nonparametric convergence rate while allowing for nonparametric or parametric estimation of the nuisance parameters. We then derive an optimal bandwidth strategy along with a procedure for estimating asymptotic confidence intervals. Finally, to illustrate the benefits of our method, we provide a numerical evaluation of our approach on a simulation along with an application to real-world medical data to analyze the effect of glycemic control on cognitive functions.