My research formalizes model multiplicity to transform the existence of multiple predictive truths into a mechanism for safe, trustworthy, and interpretable AI. I develop the theoretical foundations to characterize Rashomon sets and the optimization algorithms required to navigate them for outcomes like provable recourse and personalized alignment. My work bridges the gap between machine learning theory and the practical needs of high-stakes decision-making in healthcare and policy.
Publications
Google Scholar | dblp | * denotes equal contribution-
2026
Proceedings of the International Conference on Machine Learning (ICML), 2026spotlightProceedings of the International Conference on Machine Learning (ICML), 2026Proceedings of the International Conference on Machine Learning (ICML), 2026An oral workshop version (Transition Noise Facilitates Interpretability) appeared at the Workshop on Interpretable Policies in Reinforcement Learning @ RLC 2024Transactions on Machine Learning Research (TMLR), 2026JAIDS Journal of Acquired Immune Deficiency Syndromes, 2026When Are Simple Models Statistically Indistinguishable From the Best Possible Models?Under review, 2026 -
2025
Advances in Neural Information Processing Systems (NeurIPS), 2025spotlightAdvances in Neural Information Processing Systems (NeurIPS), 2025Medical Image Computing and Computer Assisted Intervention (MICCAI), 2025An oral workshop version (ProtoEEGNet) appeared at the Medical Imaging meets NeurIPS Workshop 2023Harvard Data Science Review, 2025won the 2022 American Statistical Association Data Challenge Expo Student CompetitionA workshop version appeared at the NeurIPS 2022 Workshop on Causality for Real-world ImpactJournal of the American Medical Informatics Association (JAMIA), 2025 -
2024
Advances in Neural Information Processing Systems (NeurIPS), 2024Proceedings of the International Conference on Machine Learning (ICML), 2024spotlightINFORMS Journal on Data Science (IJDS), 2024 -
2023
Advances in Neural Information Processing Systems (NeurIPS), 2023The Journal of Infectious Diseases (JID), 2023 -
2022
Proceedings of the ACM Conference on Fairness, Accountability, and Transparency (FAccT), 2022Statistics Surveys, 2022 -
2021
Second Workshop on Scholarly Document Processing (SDP) at NAACL, 2021oral, won third place in the 3C Shared Task Competition