publications
publications by categories in reversed chronological order.
2024
-
Towards Safe Policy Learning under Partial Identifiability: A Causal Approach\textbfThe 38th Annual AAAI Conference on Artificial Intelligence (Oral), 2024
2023
- What’s fair is… fair? Presenting JustEFAB, an ethical framework for operationalizing medical ethics and social justice in the integration of clinical machine learning: JustEFABIn Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency, 2023
- A normative framework for artificial intelligence as a sociotechnical system in healthcarePatterns, 2023
- Making machine learning matter to clinicians: model actionability in medical decision-makingNPJ Digital Medicine, 2023
-
Why did the Model Fail?: Attributing Model Performance Changes to Distribution ShiftsInternational Conference on Machine Learning (to appear), 2023 -
Learning-to-defer for sequential medical decision-making under uncertaintyTMLR, Previous version at ICML Workshop on Interpretable Machine Learning in Healthcare, 2023
2022
- Exploring Counterfactual Explanations Through the Lens of Adversarial Examples: A Theoretical and Empirical Analysis25th International Conference on Artificial Intelligence and Statistics and ICML Workshop on Algorithmic Recourse, 2022
-
Generalizing Off-Policy Evaluation From a Causal Perspective For Sequential Decision-MakingarXiv preprint at arXiv:2201.08262, Previous version appeared at ICML Workshop on Neglected Assumptions in Causal Inference, 2022 -
Towards Robust Off-Policy Evaluation via Human InputsIn AI Ethics and Society, 2022 -
Counterfactually Guided Policy Transfer in Clinical SettingsIn Proceedings of the Conference on Health, Inference, and Learning (CHIL), Shorter version at Inductive Biases, Invariances and Generalization in RL (BIG) at ICML, 2022
2021
-
Ethical Machine Learning in HealthcareAnnual Review of Biomedical Data Science, 2021 -
Pulling Up by the Causal Bootstraps: Causal Data Augmentation for Pre-training Debiasing30th ACM International Conference on Information and Knowledge Management, 2021 -
Can You Fake It Until You Make It? Impacts of Differentially Private Synthetic Data on Downstream Classification FairnessIn Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency, 2021 -
Towards Robust and Reliable Algorithmic RecourseNeural Information Processing Systems and ICML Workshop on Algorithmic Recourse, 2021 -
An empirical framework for domain generalization in clinical settingsIn Proceedings of the Conference on Health, Inference, and Learning, 2021
2020
-
Probabilistic machine learning for healthcareAnnual Review of Biomedical Data Science, 2020 -
What went wrong and when? Instance-wise Feature Importance for time-series ModelsIn NeuRIPS, 2020 - Sequential Explanations with Mental Model-Based PoliciesIn Workshop on Human Interpretability in Machine Learning at ICML, 2020
-
Confounding Feature Acquisition for Causal Effect EstimationIn Machine Learning for Health, 2020 - Patient safety and quality improvement: Ethical principles for a regulatory approach to bias in healthcare machine learningIn Journal of the American Medical Informatics Association, 2020
- Ethical limitations of algorithmic fairness solutions in healthcare machine learningIn Lancet Digital Health, 2020
- When your only tool is a hammer: ethical limitations of computational fairness solutions in healthcare machine learning (Oral)In Lancet Digital Health, AAAI Conference on AI Ethics and Society (AIES), Fair ML for Health Workshop at NeurIPS, 2020
- Treating Health Disparities with Artificial IntelligenceIn Nature Medicine, 2020
2019
- Fair and Robust Treatment Effect Estimates: Estimation Under Treatment and Outcome Disparity with Deep Neural ModelsIn Fair ML for Health Workshop at NeurIPS, 2019
- Individualized Feature Importance for Time Series Risk Prediction ModelsIn Machine Learning for Health Workshop at NeurIPS, 2019
-
What Clinicians Want: Contextualizing Explainable Machine Learning for Clinical End UseIn Machine Learning for Healthcare (MLHC), 2019 -
Towards Realistic Individual Recourse and Actionable Explanations in Black-Box Decision Making SystemsIn SafeML Workshop at the International Conference on Learning Representations (ICLR), 2019
2018
-
xGEMS: Generating Exemplars to Explain Black-Box ModelsIn , 2018 -
Co-regularized Monotone Regtargeting for Semi-supervised LeTORIn Siam International Conference on Data Mining (SDM), 2018
2016
-
Identifiable Phenotyping using Constrained Non-Negative Matrix FactorizationIn Machine Learning for Healthcare Conference (MLHC), 2016 -
Rényi divergence minimization based co-regularized multiview clusteringMachine Learning, 2016
