AIConfPaper
← Search

Valentyn Melnychuk

21 accepted papers

2026

An Orthogonal Learner for Individualized Outcomes in Markov Decision Processes

Emil Javurek, Valentyn Melnychuk, Jonas Schweisthal, Konstantin Hess, Dennis Frauen, Stefan Feuerriegel
ICLR 2026poster

Predicting individualized potential outcomes in sequential decision-making is central for optimizing therapeutic decisions in personalized medicine (e.g., which dosing sequence to give to a cancer patient). However, predicting potential out- comes over long horizons is notoriously difficult. Existi…

Cited by 0Source ↗code ↗Scholar ↗
2026

Efficient and Sharp Off-Policy Learning under Unobserved Confounding

Konstantin Hess, Dennis Frauen, Valentyn Melnychuk, Stefan Feuerriegel
ICLR 2026poster

We develop a novel method for personalized off-policy learning in scenarios with unobserved confounding. Thereby, we address a key limitation of standard policy learning: standard policy learning assumes unconfoundedness, meaning that no unobserved factors influence both treatment assignment and out…

Cited by 0Source ↗code ↗Scholar ↗
2026

Frequentist Consistency of Prior-Data Fitted Networks for Causal Estimation

Valentyn Melnychuk, Vahid Balazadeh, Stefan Feuerriegel, Rahul G. Krishnan
ICML 2026poster

Foundation models based on prior-data fitted networks (PFNs) have shown strong empirical performance in causal inference by framing it as an in-context learning problem. However, it is unclear whether PFN-based causal estimators provide uncertainty quantification that is consistent with classical fr…

Cited by 0Source ↗Scholar ↗
2026

GDR-learners: Orthogonal Learning of Generative Models for Potential Outcomes

Valentyn Melnychuk, Stefan Feuerriegel
ICLR 2026poster

Various deep generative models have been proposed to estimate potential outcomes distributions from observational data. However, none of them have the favorable theoretical property of general Neyman-orthogonality and, associated with it, quasi-oracle efficiency and double robustness. In this paper,…

Cited by 0Source ↗code ↗Scholar ↗
2026

IGC-Net for conditional average potential outcome estimation over time

Konstantin Hess, Dennis Frauen, Valentyn Melnychuk, Stefan Feuerriegel
ICLR 2026poster

Estimating potential outcomes for treatments over time based on observational data is important for personalized decision-making in medicine. However, many existing methods for this task fail to properly adjust for time-varying confounding and thus yield biased estimates. There are only a few neural…

Cited by 10Source ↗code ↗Scholar ↗
2026

Overlap-Adaptive Regularization for Conditional Average Treatment Effect Estimation

Valentyn Melnychuk, Dennis Frauen, Jonas Schweisthal, Stefan Feuerriegel
ICLR 2026poster

The conditional average treatment effect (CATE) is widely used in personalized medicine to inform therapeutic decisions. However, state-of-the-art methods for CATE estimation (so-called meta-learners) often perform poorly in the presence of low overlap. In this work, we introduce a new approach to t…

Cited by 0Source ↗Scholar ↗
2025

Conformal Prediction for Causal Effects of Continuous Treatments

Maresa Schröder, Dennis Frauen, Jonas Schweisthal, Konstantin Hess, Valentyn Melnychuk, Stefan Feuerriegel
NeurIPS 2025poster

Uncertainty quantification of causal effects is crucial for safety-critical applications such as personalized medicine. A powerful approach for this is conformal prediction, which has several practical benefits due to model-agnostic finite-sample guarantees. Yet, existing methods for conformal predi…

Cited by 0Source ↗code ↗Scholar ↗
2025

Differentially private learners for heterogeneous treatment effects

Maresa Schröder, Valentyn Melnychuk, Stefan Feuerriegel
ICLR 2025poster

Patient data is widely used to estimate heterogeneous treatment effects and understand the effectiveness and safety of drugs. Yet, patient data includes highly sensitive information that must be kept private. In this work, we aim to estimate the conditional average treatment effect (CATE) from obser…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

Treatment Effect Estimation for Optimal Decision-Making

Dennis Frauen, Valentyn Melnychuk, Jonas Schweisthal, Mihaela van der Schaar, Stefan Feuerriegel
NeurIPS 2025poster

Decision-making across various fields, such as medicine, heavily relies on conditional average treatment effects (CATEs). Practitioners commonly make decisions by checking whether the estimated CATE is positive, even though the decision-making performance of modern CATE estimators is poorly understo…

Cited by 0Source ↗Scholar ↗
2024

A Neural Framework for Generalized Causal Sensitivity Analysis

Dennis Frauen, Fergus Imrie, Alicia Curth, Valentyn Melnychuk, Stefan Feuerriegel, Mihaela van der Schaar
ICLR 2024poster

Unobserved confounding is common in many applications, making causal inference from observational data challenging. As a remedy, causal sensitivity analysis is an important tool to draw causal conclusions under unobserved confounding with mathematical guarantees. In this paper, we propose NeuralCSA,…

Cited by 11Source ↗PDF ↗code ↗Scholar ↗
2024

Bayesian Neural Controlled Differential Equations for Treatment Effect Estimation

Konstantin Hess, Valentyn Melnychuk, Dennis Frauen, Stefan Feuerriegel
ICLR 2024poster

Treatment effect estimation in continuous time is crucial for personalized medicine. However, existing methods for this task are limited to point estimates of the potential outcomes, whereas uncertainty estimates have been ignored. Needless to say, uncertainty quantification is crucial for reliable…

Cited by 16Source ↗PDF ↗code ↗Scholar ↗
2024

Bounds on Representation-Induced Confounding Bias for Treatment Effect Estimation

Valentyn Melnychuk, Dennis Frauen, Stefan Feuerriegel
ICLR 2024spotlight

State-of-the-art methods for conditional average treatment effect (CATE) estimation make widespread use of representation learning. Here, the idea is to reduce the variance of the low-sample CATE estimation by a (potentially constrained) low-dimensional representation. However, low-dimensional repre…

Cited by 11Source ↗PDF ↗code ↗Scholar ↗
2024

DiffPO: A causal diffusion model for learning distributions of potential outcomes

Yuchen Ma, Valentyn Melnychuk, Jonas Schweisthal, Stefan Feuerriegel
NeurIPS 2024poster

Predicting potential outcomes of interventions from observational data is crucial for decision-making in medicine, but the task is challenging due to the fundamental problem of causal inference. Existing methods are largely limited to point estimates of potential outcomes with no uncertain quantific…

Cited by 1Source ↗PDF ↗Scholar ↗
2024

Quantifying Aleatoric Uncertainty of the Treatment Effect: A Novel Orthogonal Learner

Valentyn Melnychuk, Stefan Feuerriegel, Mihaela van der Schaar
NeurIPS 2024poster

Estimating causal quantities from observational data is crucial for understanding the safety and effectiveness of medical treatments. However, to make reliable inferences, medical practitioners require not only estimating averaged causal quantities, such as the conditional average treatment effect,…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2023

Estimating Average Causal Effects from Patient Trajectories

Dennis Frauen, Tobias Hatt, Valentyn Melnychuk, Stefan Feuerriegel
AAAI 2023technical

In medical practice, treatments are selected based on the expected causal effects on patient outcomes. Here, the gold standard for estimating causal effects are randomized controlled trials; however, such trials are costly and sometimes even unethical. Instead, medical practice is increasingly inter…

Cited by 27Source ↗PDF ↗code ↗Scholar ↗
2023

Normalizing Flows for Interventional Density Estimation

Valentyn Melnychuk, Dennis Frauen, Stefan Feuerriegel
ICML 2023poster

Existing machine learning methods for causal inference usually estimate quantities expressed via the mean of potential outcomes (e.g., average treatment effect). However, such quantities do not capture the full information about the distribution of potential outcomes. In this work, we estimate the d…

Cited by 19Source ↗PDF ↗code ↗Scholar ↗
2023

Partial Counterfactual Identification of Continuous Outcomes with a Curvature Sensitivity Model

Valentyn Melnychuk, Dennis Frauen, Stefan Feuerriegel
NeurIPS 2023spotlight

Counterfactual inference aims to answer retrospective "what if" questions and thus belongs to the most fine-grained type of inference in Pearl's causality ladder. Existing methods for counterfactual inference with continuous outcomes aim at point identification and thus make strong and unnatural ass…

Cited by 13Source ↗PDF ↗code ↗Scholar ↗
2023

Reliable Off-Policy Learning for Dosage Combinations

Jonas Schweisthal, Dennis Frauen, Valentyn Melnychuk, Stefan Feuerriegel
NeurIPS 2023poster

Decision-making in personalized medicine such as cancer therapy or critical care must often make choices for dosage combinations, i.e., multiple continuous treatments. Existing work for this task has modeled the effect of multiple treatments independently, while estimating the joint effect has recei…

Cited by 11Source ↗PDF ↗code ↗Scholar ↗
2023

Sharp Bounds for Generalized Causal Sensitivity Analysis

Dennis Frauen, Valentyn Melnychuk, Stefan Feuerriegel
NeurIPS 2023poster

Causal inference from observational data is crucial for many disciplines such as medicine and economics. However, sharp bounds for causal effects under relaxations of the unconfoundedness assumption (causal sensitivity analysis) are subject to ongoing research. So far, works with sharp bounds are re…

Cited by 23Source ↗PDF ↗code ↗Scholar ↗
2022

Causal Transformer for Estimating Counterfactual Outcomes

Valentyn Melnychuk, Dennis Frauen, Stefan Feuerriegel
ICML 2022spotlight

Estimating counterfactual outcomes over time from observational data is relevant for many applications (e.g., personalized medicine). Yet, state-of-the-art methods build upon simple long short-term memory (LSTM) networks, thus rendering inferences for complex, long-range dependencies challenging. In…

Cited by 124Source ↗PDF ↗code ↗Scholar ↗