Search Results for author: Marco Carone

Found 7 papers, 4 papers with code

Combining T-learning and DR-learning: a framework for oracle-efficient estimation of causal contrasts

no code implementations3 Feb 2024 Lars van der Laan, Marco Carone, Alex Luedtke

We introduce efficient plug-in (EP) learning, a novel framework for the estimation of heterogeneous causal contrasts, such as the conditional average treatment effect and conditional relative risk.

Adaptive debiased machine learning using data-driven model selection techniques

no code implementations24 Jul 2023 Lars van der Laan, Marco Carone, Alex Luedtke, Mark van der Laan

For this reason, practitioners may resort to simpler models based on parametric or semiparametric assumptions.

Model Selection valid

Causal isotonic calibration for heterogeneous treatment effects

1 code implementation27 Feb 2023 Lars van der Laan, Ernesto Ulloa-Pérez, Marco Carone, Alex Luedtke

We propose causal isotonic calibration, a novel nonparametric method for calibrating predictors of heterogeneous treatment effects.

A general framework for inference on algorithm-agnostic variable importance

3 code implementations7 Apr 2020 Brian D. Williamson, Peter B. Gilbert, Noah R. Simon, Marco Carone

In many applications, it is of interest to assess the relative contribution of features (or subsets of features) toward the goal of predicting a response -- in other words, to gauge the variable importance of features.

valid

Nonparametric variable importance using an augmented neural network with multi-task learning

1 code implementation ICML 2018 Jean Feng, Brian Williamson, Noah Simon, Marco Carone

In predictive modeling applications, it is often of interest to determine the relative contribution of subsets of features in explaining the variability of an outcome.

Multi-Task Learning

Sequential Double Robustness in Right-Censored Longitudinal Models

1 code implementation6 May 2017 Alexander R. Luedtke, Oleg Sofrygin, Mark J. Van Der Laan, Marco Carone

Consider estimating the G-formula for the counterfactual mean outcome under a given treatment regime in a longitudinal study.

Methodology

An Omnibus Nonparametric Test of Equality in Distribution for Unknown Functions

no code implementations14 Oct 2015 Alexander R. Luedtke, Marco Carone, Mark J. Van Der Laan

We present a novel family of nonparametric omnibus tests of the hypothesis that two unknown but estimable functions are equal in distribution when applied to the observed data structure.

Cannot find the paper you are looking for? You can Submit a new open access paper.