Dennis Frauen

PhD Candidate & Researcher

About me

I am a third-year PhD student at LMU Munich, supervised by Stefan Feuerriegel. I am also an Ellis PhD student, where I am co-supervised by Mihaela van der Schaar (University of Cambridge). My research interest lies in the intersection of causality, machine learning, and statistics. I am interested in developing efficient, robust, and reliable machine learning methods for causal inference. This includes methods for estimating causal effects, but also topics on (partial) identification and causal sensitivity analysis. Furthermore, I use ideas from causality to make data-driven decision-making optimal and fair.

Download my CV .

Interests

Causal machine learning
Probabilistic modeling
Off-policy learning
(Causal) algorithmic fairness
Uncertainty quantification

Recent News

All news»

[26/09/2023] Together with Stefan and Abdu, we presented an overview of our research at the Ladenburger Diskurs.

[21/09/2023] Three accepted papers at NeurIPS 2023! Sharp Bounds for Generalized Causal Sensitivity Analysis, Partial Counterfactual Identification of Continuous Outcomes with a Curvature Sensitivity Model, and Reliable Off-Policy Learning for Dosage Combinations.

[24/08/2023] I presented some of our ongoing work on Causal sensitivity analysis at Microsoft Research, Cambridge.

[11/06/2023] I am excited to join the van der Schaar lab at the University of Cambridge as a visiting PhD student this summer.

[24/04/2023] Our paper Normalizing Flows for Interventional Density Estimation was accepted at ICML 2023.

Featured Publications

Dennis Frauen, Valentyn Melnychuk, Stefan Feuerriegel

December, 2023 Accepted at NeurIPS 2023

Sharp Bounds for Generalized Causal Sensitivity Analysis

We propose a framework for causal sensitivity analysis under generalized marginal sensitivity models.

Valentyn Melnychuk, Dennis Frauen, Stefan Feuerriegel

December, 2023 Accepted at NeurIPS 2023

Partial Counterfactual Identification of Continuous Outcomes with a Curvature Sensitivity Model

We investigate the problem of partial counterfactual identification and propose a novel curvature sensitivity model.

Jonas Schweisthal, Dennis Frauen, Valentyn Melnychuk, Stefan Feuerriegel

December, 2023 Accepted at NeurIPS 2023

Reliable Off-Policy Learning for Dosage Combinations

We propose a novel method for reliable off-policy learning for dosage combinations under potential overlap violations.

Valentyn Melnychuk, Dennis Frauen, Stefan Feuerriegel

July, 2023 Accepted at ICML 2023

Normalizing Flows for Interventional Density Estimation

We propose a fully-parametric deep learning method for efficient interventional density estimation based on normalizing flows.

Dennis Frauen, Stefan Feuerriegel

May, 2023 Accepted at ICLR 2023

Estimating individual treatment effects under unobserved confounding using binary instruments

We propose a multiple robust robust machine learning framework for estimating individual treatment effects under unobserved confounding when binary instruments are available.

Dennis Frauen, Tobias Hatt, Valentyn Melnychuk, Stefan Feuerriegel

February, 2023 Accepted at AAAI 2023

Estimating average causal effects from patient trajectories

We propose an efficient end-to-end deep learning model to estimate average causal effects from patient trajectories.

Valentyn Melnychuk, Dennis Frauen, Stefan Feuerriegel

June, 2022 In ICML 2022

Causal Transformer for Estimating Counterfactual Outcomes

We propose a state-of-the-art transformer-based architecture to estimate counterfactual outcomes from longitudinal observational data.

All Publications

Dennis Frauen, Fergus Imrie, Alicia Curth, Valentyn Melnychuk, Stefan Feuerriegel, Mihaela van der Schaar (2023). A Neural Framework for Generalized Causal Sensitivity Analysis. Preprint.

PDF Cite

Valentyn Melnychuk, Dennis Frauen, Stefan Feuerriegel (2023). Bounds on Representation-Induced Confounding Bias for Treatment Effect Estimation. Preprint.

PDF Cite

Maresa Schröder, Dennis Frauen, Stefan Feuerriegel (2023). Causal Fairness under Unobserved Confounding: A Neural Sensitivity Framework. Preprint.

PDF Cite

Konstantin Hess, Valentyn Melnychuk, Dennis Frauen, Stefan Feuerriegel (2023). Bayesian neural controlled differential equations for treatment effect estimation. Preprint.

PDF Cite

Yuchen Ma, Dennis Frauen, Valentyn Melnychuk, Stefan Feuerriegel (2023). Counterfactual Fairness for Predictions using Generative Adversarial Networks. Preprint.

PDF Cite

Dennis Frauen, Valentyn Melnychuk, Stefan Feuerriegel (2023). Sharp Bounds for Generalized Causal Sensitivity Analysis. Accepted at NeurIPS 2023.

PDF Cite

Valentyn Melnychuk, Dennis Frauen, Stefan Feuerriegel (2023). Partial Counterfactual Identification of Continuous Outcomes with a Curvature Sensitivity Model. Accepted at NeurIPS 2023.

PDF Cite

Jonas Schweisthal, Dennis Frauen, Valentyn Melnychuk, Stefan Feuerriegel (2023). Reliable Off-Policy Learning for Dosage Combinations. Accepted at NeurIPS 2023.

PDF Cite

Valentyn Melnychuk, Dennis Frauen, Stefan Feuerriegel (2023). Normalizing Flows for Interventional Density Estimation. Accepted at ICML 2023.

PDF Cite Code

Dennis Frauen, Stefan Feuerriegel (2023). Estimating individual treatment effects under unobserved confounding using binary instruments. Accepted at ICLR 2023.

PDF Cite Code

Dennis Frauen, Valentyn Melnychuk, Stefan Feuerriegel (2023). Fair Off-Policy Learning from Observational Data. Preprint.

PDF Cite

Dennis Frauen, Tobias Hatt, Valentyn Melnychuk, Stefan Feuerriegel (2023). Estimating average causal effects from patient trajectories. Accepted at AAAI 2023.

PDF Cite Code

Valentyn Melnychuk, Dennis Frauen, Stefan Feuerriegel (2022). Causal Transformer for Estimating Counterfactual Outcomes. In ICML 2022.

PDF Cite Code