no code implementations • 15 Apr 2024 • Razieh Nabi, Nima S. Hejazi, Mark J. Van Der Laan, David Benkeser
Constrained learning has become increasingly important, especially in the realm of algorithmic fairness and machine learning.
no code implementations • 28 Sep 2023 • Ashkan Ertefaie, Luke Duttweiler, Brent A. Johnson, Mark J. Van Der Laan
Third, we provide consistency and convergence rate for the optimizer of the regimen-response curve estimator; this enables us to estimate an optimal semiparametric rule.
no code implementations • 27 Jan 2023 • Ivana Malenica, Rachael V. Phillips, Daniel Lazzareschi, Jeremy R. Coyle, Romain Pirracchio, Mark J. Van Der Laan
We propose a novel, fully nonparametric approach for the multi-task learning, the Multi-task Highly Adaptive Lasso (MT-HAL).
no code implementations • 5 Dec 2022 • Ivana Malenica, Jeremy R. Coyle, Mark J. Van Der Laan, Maya L. Petersen
Our causal target parameter is the mean latent outcome we would have obtained after one time-step, if, starting at time t given the observed past, we had carried out a stochastic intervention that maximizes the outcome under a resource constraint.
no code implementations • 23 Oct 2021 • Mark J. Van Der Laan, Sherri Rose
The growth of machine learning as a field has been accelerating with increasing interest and publications across fields, including statistics, but predominantly in computer science.
no code implementations • 21 Sep 2021 • Ivana Malenica, Rachael V. Phillips, Romain Pirracchio, Antoine Chambaz, Alan Hubbard, Mark J. Van Der Laan
In this work, we introduce the Personalized Online Super Learner (POSL) -- an online ensembling algorithm for streaming data whose optimization procedure accommodates varying degrees of personalization.
no code implementations • 29 Jan 2021 • Ivana Malenica, Aurelien Bibaut, Mark J. Van Der Laan
The current work is motivated by the need for robust statistical methods for precision medicine; as such, we address the need for statistical methods that provide actionable inference for a single unit at any point in time.
no code implementations • 12 Jun 2020 • Jeremy R. Coyle, Nima S. Hejazi, Ivana Malenica, Rachael V. Phillips, Benjamin F. Arnold, Andrew Mertens, Jade Benjamin-Chung, Weixin Cai, Sonali Dayal, John M. Colford Jr., Alan E. Hubbard, Mark J. Van Der Laan
Targeted Learning is a subfield of statistics that unifies advances in causal inference, machine learning and statistical theory to help answer scientifically impactful questions with statistical confidence.
no code implementations • 5 Jun 2020 • Aurélien F. Bibaut, Antoine Chambaz, Mark J. Van Der Laan
To the best of our knowledge, our proposal is the first one to be rate-adaptive for a collection of general black-box contextual bandit algorithms: it achieves the same regret rate as the best candidate.
2 code implementations • 22 May 2020 • Ashkan Ertefaie, Nima S. Hejazi, Mark J. Van Der Laan
We propose a class of nonparametric inverse probability weighted estimators in which the weighting mechanism is estimated via undersmoothing of the highly adaptive lasso, a nonparametric regression function proven to converge at $n^{-1/3}$-rate to the true weighting mechanism.
3 code implementations • 30 Mar 2020 • Nima S. Hejazi, Mark J. Van Der Laan, Holly E. Janes, Peter B. Gilbert, David C. Benkeser
We propose nonparametric methodology for efficiently estimating a counterfactual parameter that quantifies the impact of a given immune response marker on the subsequent probability of infection.
Methodology
no code implementations • 5 Mar 2020 • Aurélien F. Bibaut, Antoine Chambaz, Mark J. Van Der Laan
We propose the Generalized Policy Elimination (GPE) algorithm, an oracle-efficient contextual bandit (CB) algorithm inspired by the Policy Elimination algorithm of \cite{dudik2011}.
no code implementations • 13 Dec 2019 • Aurélien F. Bibaut, Ivana Malenica, Nikos Vlassis, Mark J. Van Der Laan
We study the problem of off-policy evaluation (OPE) in Reinforcement Learning (RL), where the aim is to estimate the performance of a new policy given historical data that may have been generated by a different policy, or policies.
2 code implementations • 25 Jul 2018 • Laura B. Balzer, Diane V. Havlir, Joshua Schwab, Mark J. Van Der Laan, Maya L. Petersen
This document provides the analytic plan for evaluating adult HIV incidence, health, and implementation outcomes for the first phase of the SEARCH Study.
Applications
no code implementations • 18 Jun 2018 • Cheng Ju, David Benkeser, Mark J. Van Der Laan
Many estimators of the average effect of a treatment on an outcome require estimation of the propensity score, the outcome regression, or both.
no code implementations • 31 Mar 2018 • Cheng Ju, Antoine Chambaz, Mark J. Van Der Laan
Say that the above product is not fast enough and the algorithm for the $G$-component is fine-tuned by a real-valued $h$.
1 code implementation • 16 Oct 2017 • Nima S. Hejazi, Sara Kherad-Pajouh, Mark J. Van Der Laan, Alan E. Hubbard
The widespread availability of high-dimensional biological data has made the simultaneous screening of many biological characteristics a central problem in computational biology and allied sciences.
Methodology
1 code implementation • 18 Jul 2017 • Cheng Ju, Joshua Schwab, Mark J. Van Der Laan
Even if the positivity assumption holds, practical violations of this assumption may jeopardize the finite sample performance of the causal estimator.
no code implementations • 30 Jun 2017 • Cheng Ju, Richard Wyss, Jessica M. Franklin, Sebastian Schneeweiss, Jenny Häggström, Mark J. Van Der Laan
Collaborative minimum loss-based estimation (C-TMLE) is a novel methodology for causal inference that takes into account information on the causal parameter of interest when selecting a PS model.
no code implementations • 8 Jun 2017 • Laura B. Balzer, Wenjing Zheng, Mark J. Van Der Laan, Maya L. Petersen
Incorporating working assumptions during estimation is more robust than assuming they hold in the underlying causal model.
Methodology
no code implementations • 27 May 2017 • Oleg Sofrygin, Zheng Zhu, Julie A Schmittdiel, Alyce S. Adams, Richard W. Grant, Mark J. Van Der Laan, Romain Neugebauer
Electronic health records (EHR) data provide a cost and time-effective opportunity to conduct cohort studies of the effects of multiple time-point interventions in the diverse patient population found in real-world clinical settings.
1 code implementation • 23 May 2017 • Elizabeth L. Ogburn, Oleg Sofrygin, Ivan Diaz, Mark J. Van Der Laan
We describe semiparametric estimation and inference for causal effects using observational data from a single social network.
Methodology Statistics Theory Statistics Theory
1 code implementation • 6 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
1 code implementation • 5 Apr 2017 • Cheng Ju, Aurélien Bibaut, Mark J. Van Der Laan
In this work, we investigated multiple widely used ensemble methods, including unweighted averaging, majority voting, the Bayes Optimal Classifier, and the (discrete) Super Learner, for image recognition tasks, with deep neural networks as candidate algorithms.
no code implementations • 7 Mar 2017 • Cheng Ju, Mary Combs, Samuel D Lendle, Jessica M. Franklin, Richard Wyss, Sebastian Schneeweiss, Mark J. Van Der Laan
In this study, we applied and evaluated the performance of the SL in its ability to predict treatment assignment using three electronic healthcare databases.
no code implementations • 14 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.