Publications

My research focuses on causal machine learning for reliable decision‑making, with an emphasis on developing flexible methods that estimate heterogeneous treatment effects under complex data structures. I design algorithms that incorporate uncertainty quantification, robustness to model misspecification, and ethical constraints, enabling trustworthy estimation even in sensitive or high‑stakes settings. A central goal of my work is to ensure that these methods are both theoretically rigorous and practically applicable to real‑world problems in business, economics, and healthcare.

You can also find all papers on my Google Scholar profile.

2025

  1. NeurIPS
    Conformal prediction for causal effects of continuous treatments
    Maresa Schröder, Dennis Frauen, Jonas Schweisthal, Konstantin Hess, Valentyn Melnychuk, and Stefan Feuerriegel
    In Conference on Neural Information Processing Systems (NeurIPS), 2025
  2. NeurIPS
    Orthogonal Survival Learners for Estimating Heterogeneous Treatment Effects from Time-to-Event Data
    Dennis Frauen*, Maresa Schröder*, Konstantin Hess, and Stefan Feuerriegel
    In Conference on Neural Information Processing Systems (NeurIPS), 2025
    (*equal contribution)
  3. ICML
    Learning representations of instruments for partial identification of treatment effects
    Jonas Schweisthal, Dennis Frauen, Maresa Schröder, Konstantin Hess, Niki Kilbertus, and Stefan Feuerriegel
    In International Conference on Machine Learning (ICML), 2025
  4. ICLR
    Differentially private learners for heterogeneous treatment effects
    Maresa Schröder, Valentyn Melnychuk, and Stefan Feuerriegel
    In International Conference on Learning Representations (ICLR), 2025
  5. ICLR
    Constructing confidence intervals for average treatment effects from multiple datasets
    Yuxin Wang, Maresa Schröder, Dennis Frauen, Jonas Schweisthal, Konstantin Hess, and Stefan Feuerriegel
    In International Conference on Learning Representations (ICLR), 2025
  6. Preprint
    PrivATE: Differentially Private Confidence Intervals for Average Treatment Effects
    Maresa Schröder, Justin Hartenstein, and Stefan Feuerriegel
    arXiv preprint, 2025
  7. Preprint
    SurvDiff: A Diffusion Model for Generating Synthetic Data in Survival Analysis
    Marie Brockschmidt, Maresa Schröder, and Stefan Feuerriegel
    arXiv preprint, 2025
  8. Preprint
    Spatial Deconfounder: Interference-Aware Deconfounding for Spatial Causal Inference
    Ayush Khot, Miruna Oprescu, Maresa Schröder, Ai Kagawa, and Xihaier Luo
    arXiv preprint, 2025
  9. Preprint
    Assessing the robustness of heterogeneous treatment effects in survival analysis under informative censoring
    Yuxin Wang, Dennis Frauen, Jonas Schweisthal, Maresa Schröder, and Stefan Feuerriegel
    arXiv preprint, 2025

2024

  1. ICLR
    Causal fairness under unobserved confounding: A neural sensitivity framework
    Maresa Schröder, Dennis Frauen, and Stefan Feuerriegel
    In International Conference on Learning Representations (ICLR), 2024

2023

  1. MAKE
    What about the Latent Space? The Need for Latent Feature Saliency Detection in Deep Time Series Classification
    Maresa Schröder, Alireza Zamanian, and Narges Ahmidi
    Machine Learning and Knowledge Extraction, 2023
  2. Workshop
    Post-hoc saliency methods fail to capture latent feature importance in time series data
    Maresa Schröder, Alireza Zamanian, and Narges Ahmidi
    In International Workshop on Trustworthy Machine Learning for Healthcare, 2023

2021

  1. Preprint
    Automatic gait analysis during steady and unsteady walking using a smartphone
    Arshad Sher, David Langford, Einar Dogger, Dan Monaghan, Luke Ian Lunn, Maresa Schröder, Azam Hamidinekoo, Marco Arkesteijn, Qiang Shen, Reyer Zwiggelaar, Helen Tench, Federico Villagra, and Otar Akanyeti
    TechRxiv preprint, 2021