Mihaela van der Schaar

The Synergy of LLMs & RL Unlocks Offline Learning of Generalizable Language-Conditioned Policies with Low-fidelity Data ICML 2025 Stochastic Encodings for Active Feature Acquisition ICML 2025 Unified Screening for Multiple Diseases ICML 2025 Preference Learning for AI Alignment: a Causal Perspective ICML 2025 Skip the Equations: Learning Behavior of Personalized Dynamical Systems Directly From Data ICML 2025 Continuously Updating Digital Twins using Large Language Models ICML 2025 Autoformulation of Mathematical Optimization Models Using LLMs ICML 2025 G-Sim: Generative Simulations with Large Language Models and Gradient-Free Calibration ICML 2025 Inverse Reinforcement Learning Meets Large Language Model Alignment ACL 2025 Decision Tree Induction Through LLMs via Semantically-Aware Evolution ICLR 2025 No Equations Needed: Learning System Dynamics Without Relying on Closed-Form ODEs ICLR 2025 Towards Automated Knowledge Integration From Human-Interpretable Representations ICLR 2025 Active Task Disambiguation with LLMs ICLR 2025 Going Beyond Static: Understanding Shifts with Time-Series Attribution ICLR 2025 Risk-Sensitive Diffusion: Robustly Optimizing Diffusion Models with Noisy Samples ICLR 2025 Position: Truly Self-Improving Agents Require Intrinsic Metacognitive Learning ICML 2025 Position: All Current Generative Fidelity and Diversity Metrics are Flawed ICML 2025 Towards Regulatory-Confirmed Adaptive Clinical Trials: Machine Learning Opportunities and Solutions AISTATS 2025 Beyond Size-Based Metrics: Measuring Task-Specific Complexity in Symbolic Regression AISTATS 2025 Active Feature Acquisition for Personalised Treatment Assignment AISTATS 2025 Visualizing token importance for black-box language models AISTATS 2025 Differentiable Causal Structure Learning with Identifiability by NOTIME AISTATS 2025 Position: Not All Explanations for Deep Learning Phenomena Are Equally Valuable ICML 2025 AutoCATE: End-to-End, Automated Treatment Effect Estimation ICML 2025 Bootstrapping Self-Improvement of Language Model Programs for Zero-Shot Schema Matching ICML 2025 Strategic Planning: A Top-Down Approach to Option Generation ICML 2025 Statistical Hypothesis Testing for Auditing Robustness in Language Models ICML 2025 L2MAC: Large Language Model Automatic Computer for Extensive Code Generation ICLR 2024 Dissecting Sample Hardness: A Fine-Grained Analysis of Hardness Characterization Methods for Data-Centric AI ICLR 2024 Towards Transparent Time Series Forecasting ICLR 2024 Defining Expertise: Applications to Treatment Effect Estimation ICLR 2024 ODE Discovery for Longitudinal Heterogeneous Treatment Effects Inference ICLR 2024 On Error Propagation of Diffusion Models ICLR 2024 Soft Mixture Denoising: Beyond the Expressive Bottleneck of Diffusion Models ICLR 2024 A Neural Framework for Generalized Causal Sensitivity Analysis ICLR 2024 Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RL ICLR 2024 Active Learning with LLMs for Partially Observed and Cost-Aware Scenarios NIPS 2024 Self-Healing Machine Learning: A Framework for Autonomous Adaptation in Real-World Environments NIPS 2024 Automatically Learning Hybrid Digital Twins of Dynamical Systems NIPS 2024 Discovering Preference Optimization Algorithms with and for Large Language Models NIPS 2024 Data-Driven Discovery of Dynamical Systems in Pharmacology using Large Language Models NIPS 2024 A theoretical design of concept sets: improving the predictability of concept bottleneck models NIPS 2024 Quantifying Aleatoric Uncertainty of the Treatment Effect: A Novel Orthogonal Learner NIPS 2024 Context-Aware Testing: A New Paradigm for Model Testing with Large Language Models NIPS 2024 Deep Learning Through A Telescoping Lens: A Simple Model Provides Empirical Insights On Grokking, Gradient Boosting & Beyond NIPS 2024 Discovering Features with Synergistic Interactions in Multiple Views ICML 2024 Time Series Diffusion in the Frequency Domain ICML 2024 Position: Why Tabular Foundation Models Should Be a Research Priority ICML 2024 Adaptive Experiment Design with Synthetic Controls AISTATS 2024 DAGnosis: Localized Identification of Data Inconsistencies using Structures AISTATS 2024 Shape Arithmetic Expressions: Advancing Scientific Discovery Beyond Closed-Form Equations AISTATS 2024 Dense Reward for Free in Reinforcement Learning from Human Feedback ICML 2024 Curated LLM: Synergy of LLMs and Data Curation for tabular augmentation in low-data regimes ICML 2024 Meta-Learners for Partially-Identified Treatment Effects Across Multiple Environments ICML 2024 Relaxed Quantile Regression: Prediction Intervals for Asymmetric Noise ICML 2024 Large Language Models to Enhance Bayesian Optimization ICLR 2024 Accounting For Informative Sampling When Learning to Forecast Treatment Outcomes Over Time ICML 2023 Differentiable and Transportable Structure Learning ICML 2023 Improving Adaptive Conformal Prediction Using Self-Supervised Learning AISTATS 2023 SurvivalGAN: Generating Time-to-Event Data for Survival Analysis AISTATS 2023 AllSim: Simulating and Benchmarking Resource Allocation Policies in Multi-User Systems NIPS 2023 Can You Rely on Your Model Evaluation? Improving Model Evaluation with Synthetic Test Data NIPS 2023 Accountability in Offline Reinforcement Learning: Explaining Decisions with a Corpus of Examples NIPS 2023 Synthcity: a benchmark framework for diverse use cases of tabular synthetic data NIPS 2023 What is Flagged in Uncertainty Quantification? Latent Density Models for Uncertainty Categorization NIPS 2023 Risk-Averse Active Sensing for Timely Outcome Prediction under Cost Pressure NIPS 2023 Joint Training of Deep Ensembles Fails Due to Learner Collusion NIPS 2023 D-CIPHER: Discovery of Closed-form Partial Differential Equations NIPS 2023 Reimagining Synthetic Tabular Data Generation through Data-Centric AI: A Comprehensive Benchmark NIPS 2023 Active Observing in Continuous-time Control NIPS 2023 A U-turn on Double Descent: Rethinking Parameter Counting in Statistical Learning NIPS 2023 Evaluating the Robustness of Interpretability Methods through Explanation Invariance and Equivariance NIPS 2023 TRIAGE: Characterizing and auditing training data for improved regression NIPS 2023 Synthetic Data, Real Errors: How (Not) to Publish and Use Synthetic Data ICML 2023 Learning Representations without Compositional Assumptions ICML 2023 In Search of Insights, Not Magic Bullets: Towards Demystification of the Model Selection Dilemma in Heterogeneous Treatment Effect Estimation ICML 2023 Adaptive Identification of Populations with Treatment Benefit in Clinical Trials: Machine Learning Challenges and Solutions ICML 2023 Deep Generative Symbolic Regression ICLR 2023 When to Make and Break Commitments? ICLR 2023 TANGOS: Regularizing Tabular Neural Networks through Gradient Orthogonalization and Specialization ICLR 2023 Neural Laplace Control for Continuous-time Delayed Systems AISTATS 2023 T-Phenotype: Discovering Phenotypes of Predictive Temporal Patterns in Disease Progression AISTATS 2023 Membership Inference Attacks against Synthetic Data through Overfitting Detection AISTATS 2023 To Impute or not to Impute? Missing Data in Treatment Effect Estimation AISTATS 2023 Understanding the Impact of Competing Events on Heterogeneous Treatment Effect Estimation from Time-to-Event Data AISTATS 2023 GOGGLE: Generative Modelling for Tabular Data by Learning Relational Structure ICLR 2023 Synthetic Model Combination: An Instance-wise Approach to Unsupervised Ensemble Learning NIPS 2022 Data-SUITE: Data-centric identification of in-distribution incongruous examples ICML 2022 Inferring Lexicographically-Ordered Rewards from Preferences AAAI 2022 Data-IQ: Characterizing subgroups with heterogeneous outcomes in tabular data NIPS 2022 Continuous-Time Modeling of Counterfactual Outcomes Using Neural Controlled Differential Equations ICML 2022 Inverse Online Learning: Understanding Non-Stationary and Reactionary Policies ICLR 2022 Benchmarking Heterogeneous Treatment Effect Models through the Lens of Interpretability NIPS 2022 Concept Activation Regions: A Generalized Framework For Concept-Based Explanations NIPS 2022 Online Decision Mediation NIPS 2022 Neural graphical modelling in continuous-time: consistency guarantees and algorithms ICLR 2022 Identifiable Energy-based Representations: An Application to Estimating Heterogeneous Causal Effects AISTATS 2022 POETREE: Interpretable Policy Learning with Adaptive Decision Trees ICLR 2022 Self-Supervision Enhanced Feature Selection with Correlated Gates ICLR 2022 D-CODE: Discovering Closed-form ODEs from Observed Trajectories ICLR 2022 How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Models ICML 2022 Label-Free Explainability for Unsupervised Models ICML 2022 Neural Laplace: Learning diverse classes of differential equations in the Laplace domain ICML 2022 Inverse Contextual Bandits: Learning How Behavior Evolves over Time ICML 2022 HyperImpute: Generalized Iterative Imputation with Automatic Model Selection ICML 2022 Composite Feature Selection Using Deep Ensembles NIPS 2022 Transfer Learning on Heterogeneous Feature Spaces for Treatment Effects Estimation NIPS 2022 A kernel two-sample test with selection bias UAI 2021 SyncTwin: Treatment Effect Estimation with Longitudinal Outcomes NIPS 2021 Invariant Causal Imitation Learning for Generalizable Policies NIPS 2021 Conformal Time-series Forecasting NIPS 2021 Integrating Expert ODEs into Neural ODEs: Pharmacology and Disease Progression NIPS 2021 Explaining Latent Representations with a Corpus of Examples NIPS 2021 On Inductive Biases for Heterogeneous Treatment Effect Estimation NIPS 2021 DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networks NIPS 2021 Closing the loop in medical decision support by understanding clinical decision-making: A case study on organ transplantation NIPS 2021 Estimating Multi-cause Treatment Effects via Single-cause Perturbation NIPS 2021 MIRACLE: Causally-Aware Imputation via Learning Missing Data Mechanisms NIPS 2021 SurvITE: Learning Heterogeneous Treatment Effects from Time-to-Event Data NIPS 2021 Time-series Generation by Contrastive Imitation NIPS 2021 A Variational Information Bottleneck Approach to Multi-Omics Data Integration AISTATS 2021 Nonparametric Estimation of Heterogeneous Treatment Effects: From Theory to Learning Algorithms AISTATS 2021 Learning Matching Representations for Individualized Organ Transplantation Allocation AISTATS 2021 SDF-Bayes: Cautious Optimism in Safe Dose-Finding Clinical Trials with Drug Combinations and Heterogeneous Patient Groups AISTATS 2021 Clairvoyance: A Pipeline Toolkit for Medical Time Series ICLR 2021 Generative Time-series Modeling with Fourier Flows ICLR 2021 Explaining by Imitating: Understanding Decisions by Interpretable Policy Learning ICLR 2021 Scalable Bayesian Inverse Reinforcement Learning ICLR 2021 Learning "What-if" Explanations for Sequential Decision-Making ICLR 2021 Policy Analysis using Synthetic Controls in Continuous-Time ICML 2021 Learning Queueing Policies for Organ Transplantation Allocation using Interpretable Counterfactual Survival Analysis ICML 2021 Explaining Time Series Predictions with Dynamic Masks ICML 2021 Inverse Decision Modeling: Learning Interpretable Representations of Behavior ICML 2021 Application of kernel hypothesis testing on set-valued data UAI 2021 Temporal Phenotyping using Deep Predictive Clustering of Disease Progression ICML 2020 Inverse Active Sensing: Modeling and Understanding Timely Decision-Making ICML 2020 Unlabelled Data Improves Bayesian Uncertainty Calibration under Covariate Shift ICML 2020 Time Series Deconfounder: Estimating Treatment Effects over Time in the Presence of Hidden Confounders ICML 2020 Frequentist Uncertainty in Recurrent Neural Networks via Blockwise Influence Functions ICML 2020 Discriminative Jackknife: Quantifying Uncertainty in Deep Learning via Higher-Order Influence Functions ICML 2020 Estimating counterfactual treatment outcomes over time through adversarially balanced representations ICLR 2020 Target-Embedding Autoencoders for Supervised Representation Learning ICLR 2020 OrganITE: Optimal transplant donor organ offering using an individual treatment effect NIPS 2020 Learning outside the Black-Box: The pursuit of interpretable models NIPS 2020 Estimating the Effects of Continuous-valued Interventions using Generative Adversarial Networks NIPS 2020 VIME: Extending the Success of Self- and Semi-supervised Learning to Tabular Domain NIPS 2020 When and How to Lift the Lockdown? Global COVID-19 Scenario Analysis and Policy Assessment using Compartmental Gaussian Processes NIPS 2020 Strictly Batch Imitation Learning by Energy-based Distribution Matching NIPS 2020 Robust Recursive Partitioning for Heterogeneous Treatment Effects with Uncertainty Quantification NIPS 2020 Gradient Regularized V-Learning for Dynamic Treatment Regimes NIPS 2020 CASTLE: Regularization via Auxiliary Causal Graph Discovery NIPS 2020 Learning for Dose Allocation in Adaptive Clinical Trials with Safety Constraints ICML 2020 KnockoffGAN: Generating Knockoffs for Feature Selection using Generative Adversarial Networks ICLR 2019 Differentially Private Bagging: Improved utility and cheaper privacy than subsample-and-aggregate NIPS 2019 Validating Causal Inference Models via Influence Functions ICML 2019 Demystifying Black-box Models with Symbolic Metamodels NIPS 2019 Attentive State-Space Modeling of Disease Progression NIPS 2019 INVASE: Instance-wise Variable Selection using Neural Networks ICLR 2019 PATE-GAN: Generating Synthetic Data with Differential Privacy Guarantees ICLR 2019 Boosting Transfer Learning with Survival Data from Heterogeneous Domains AISTATS 2019 Conditional Independence Testing using Generative Adversarial Networks NIPS 2019 Time-series Generative Adversarial Networks NIPS 2019 Multitask Boosting for Survival Analysis with Competing Risks NIPS 2018 Deep Sensing: Active Sensing using Multi-directional Recurrent Neural Networks ICLR 2018 GANITE: Estimation of Individualized Treatment Effects using Generative Adversarial Nets ICLR 2018 A Hidden Absorbing Semi-Markov Model for Informatively Censored Temporal Data: Learning and Inference JMLR 2018 Boosted Trees for Risk Prognosis MLHC 2018 Disease-Atlas: Navigating Disease Trajectories using Deep Learning MLHC 2018 Bayesian Inference of Individualized Treatment Effects using Multi-task Gaussian Processes NIPS 2017 DPSCREEN: Dynamic Personalized Screening NIPS 2017 A Non-parametric Learning Method for Confidently Estimating Patient's Clinical State and Dynamics NIPS 2016 Balancing Suspense and Surprise: Timely Decision Making with Endogenous Information Acquisition NIPS 2016 Global Multi-armed Bandits with Hölder Continuity AISTATS 2015 Discovering, Learning and Exploiting Relevance NIPS 2014