I am an assistant professor in the School of Operations Research and Information Engineering and Cornell Tech at Cornell University. I am a field member of ORIE, Center for Applied Mathematics (CAM), Statistics, ECE, and CS. I am affiliated with WCM Institute of AI for Digital Health. Prior to Cornell Tech, I was a postdoctoral fellow at the Statistical Reinforcement Lab at Harvard University. I received my Ph.D. in Operations Research in 2022 from Carnegie Mellon University. I received my B.A.s in Mathematics and Economics from Smith College in 2017.
My lab aims to develop a robust, end-to-end framework for generating and implementing evidence-based personalized healthcare strategies that are statistically sound and practically feasible in real-world clinical settings. Our work is fundamentally motivated by the unique challenges of healthcare applications, where high-stakes decision-making, limited sample sizes, and the need for minimal yet defensible statistical assumptions demand methods that are not only rigorous but also efficient and interpretable.
The pipeline begins with leveraging observational data to generate initial evidence and hypotheses using scalable causal discovery methods that are efficient under finite-samples and robust under unobserved variables. This involves designing novel causal discovery algorithms, improving the efficiency of nonparametric conditional indepndent tests, and leverge modern machine learning methods such as diffusion to handle unobserved variables.
To validate these findings, we focuses on the effcient design of adaptive clinical trials (such as micro-randomized trials (MRTs) and N-of-1 trials) under practical constraints, which provide rigorous, dynamic, and individualized causal evidence. Our methodology involves two distinct strands: (1) designing approximation algorithms for constrained, simpler problems, and (2) reformulating restless bandit problems to develop algorithms with stronger finite-sample guarantees.
Further, we are interested in developing efficient and robust statistical inference methods in varies settings to ensure that results are statistically sound and reproducible. This includes developing theory and tools that are valid for non-adaptively collected data, data generated through adaptive algorithms (e.g., bandits or sequential trials), and decentralized (federated) data environments.
We are broadly interested in translating research into practice by collaborating directly with clinicians to tackle pressing challenges: improving heart failure care, creating interpretable clinical LLMs, and leveraging diffusion models for single-cell genomics. A copy of my CV can be found here.
AWS Credit Grants – Cornell’s Center for Data Science for Enterprise and Society
My work has been recognized by the following awards:
Finalist, 2023 INFORMS DMDA Workshop Best Paper Competition -- Theoretical Track
Winner, 2021 INFORMS Pierskalla Best Paper Award
Winner, 2021 CHOW Best Student Paper in the Category of Operations Research and Management Science
Finalist, 2019 INFORMS IBM Service Science Best Student Paper Award
Tata Consultancy Services Fellowship, Tepper School of Business, CMU, 2020
Ann Kirsten Pokora Prize, Department of Mathematics, Smith College, 2017
My lab aims to develop a robust, end-to-end framework for generating and implementing evidence-based personalized healthcare strategies that are statistically sound and practically feasible in real-world clinical settings. Our work is fundamentally motivated by the unique challenges of healthcare applications, where high-stakes decision-making, limited sample sizes, and the need for minimal yet defensible statistical assumptions demand methods that are not only rigorous but also efficient and interpretable.
The pipeline begins with leveraging observational data to generate initial evidence and hypotheses using scalable causal discovery methods that are efficient under finite-samples and robust under unobserved variables. This involves designing novel causal discovery algorithms, improving the efficiency of nonparametric conditional indepndent tests, and leverge modern machine learning methods such as diffusion to handle unobserved variables.
To validate these findings, we focuses on the effcient design of adaptive clinical trials (such as micro-randomized trials (MRTs) and N-of-1 trials) under practical constraints, which provide rigorous, dynamic, and individualized causal evidence. Our methodology involves two distinct strands: (1) designing approximation algorithms for constrained, simpler problems, and (2) reformulating restless bandit problems to develop algorithms with stronger finite-sample guarantees.
Further, we are interested in developing efficient and robust statistical inference methods in varies settings to ensure that results are statistically sound and reproducible. This includes developing theory and tools that are valid for non-adaptively collected data, data generated through adaptive algorithms (e.g., bandits or sequential trials), and decentralized (federated) data environments.
We are broadly interested in translating research into practice by collaborating directly with clinicians to tackle pressing challenges: improving heart failure care, creating interpretable clinical LLMs, and leveraging diffusion models for single-cell genomics. A copy of my CV can be found here.
Funding and Awards
My research is supported byGroup
PhD Advisees:Current and Past Student Collaborators:
Methodological Work
- When Additive Noise Meets Unobserved Mediators: Bivariate Denoising Diffusion for Causal Discovery with Dominik Meier, Sujai Hiremath, Promit Ghosal (arXiv)
- Optimal Adjustment Sets for Nonparametric Estimation of Weighted Controlled Direct Effect with Ruiyang Lin, Yongyi Guo (arXiv)
- MOSIC: Model-Agnostic Optimal Subgroup Identification with Multi-Constraint for Improved Reliability with Wenxin Chen, Weishen Pan, Fei Wang (arXiv)
- From Restless to Contextual: A Thresholding Bandit Approach to Improve Finite-Horizon Performance with Jiamin Xu, Ivan Nazarov, Aditya Rastogi, Africa Perianez (arXiv)
- Online Uniform Sampling: Randomized Learning-Augmented Approximation Algorithms with Application to Digital Health with Xueqing Liu, Esmaeil Keyvanshokooh, and Susan A. Murphy (arXiv)
- LoSAM: Local Search in Additive Noise Models with Mixed Mechanisms and General Noise for Global Causal Discovery with Sujai Hiremath, Promit Ghosal (arXiv) (UAI 2025)
- Reward Maximization for Pure Exploration: Minimax Optimal Good Arm Identification for Nonparametric Multi-Armed Bandits with Brian Cho, Dominik Meier, Nathan Kallus (arXiv) (AISTATS 2025)
- CSPI-MT: Calibrated Safe Policy Improvement with Multiple Testing for Threshold Policies with Brian Cho, Ana-Roxana Pop, Sam Corbett-Davies, Israel Nir, Ariel Evnine, Nathan Kallus (arXiv) (KDD 2025)
- Local Causal Discovery for Structural Evidence of Direct Discrimination with Jacqueline Maasch, Violet Chen, Agni Orfanoudaki, Nil-Jana Akpinar, Fei Wang (arXiv) (AAAI 2025)
- Hybrid Top-Down Global Causal Discovery with Local Search for Linear and Nonlinear Additive Noise Models with Sujai Hiremath, Jaqueline Maasch, Mengxiao Gao, Promit Ghosal (arXiv) (NeurIPS 2024)
- Peeking with PEAK: Sequential, Nonparametric Composite Hypothesis Tests for Means of Multiple Data Streams with Brian Cho and Nathan Kallus (arXiv)(ICML 2024)
- Kernel Debiased Plug-in Estimation: Simultaneous, Automated Debiasing without Influence Functions for Many Target Parameters with Brian Cho, Yaroslav Mukhin, and Ivana Malenica (arXiv)(ICML 2024)
- Finalist, 2023 INFORMS DMDA Workshop Best Paper Competition -- Theoretical Track
- Local Discovery by Partitioning: Polynomial-Time Causal Discovery Around Exposure-Outcome Pairs with Jacqueline Maasch, Weishen Pan, Shantanu Gupta, Volodymyr Kuleshov, Fei Wang (arXiv) (UAI 2024
Review, Workshop Publication, and Applied Work
- Federated Causal Inference in Healthcare: Methods, Challenges, and Application with Haoyang Li, Jie Xu, Fei Wang, Chengxi Zang (arXiv)
- Anytime-Valid Inference in N-of-1 Trials with Ivana Malenica, Yongyi Guo, and Stefan Konigorski (arXiv) (Machine Learning for Health symposium 2023, ML4H 2023)
- Awarding Additional MELD Points to the Shortest Waitlist Candidates Improves Sex Disparity in Access to Liver Transplant in the United States with Sarah Bernards, Eric Lee, Ngai Leung, Mustafa Akan, Huan Zhao, Monika Sarkar, Sridhar Tayur, Neil Mehta (American Journal of Transplant 2022)
- Machine Learning Algorithms in Predicting Hospital Readmissions in Sickle Cell Disease with Arisha Patel, Andrew Li, Jeremy Weiss, Seyed Mehdi Nouraie, Sridhar Tayur, and Enrico M Novelli (British Journal of Haematology, 2020) (Extended abstract at ASH Annual Meeting & Exposition 2019)
- Data Visualization of Agent-Based Modeling of Virus Spread with Dominique Thiebaut
INFOCOMP, 2017 (INFOCOMP 2017;PDF) (Source code)
Teaching
- Fall 2023, 2024, 2025, CS 5785/ORIE 5750/ECE 5414, Applied Machine Learning
- Spring 2025, ORIE 5217: Digital N-of-1 Trials and Their Application
- Spring 2024, ORIE 7790: Selected topics in Applied Statistics - Statistical and Optimization Methods for Decision-Making in Healthcare