Research

  1. Bandit/RL Algorithms
    Contextual Thompson Sampling via Generation of Missing Data
    Kelly W Zhang, Tiffany (Tianhui) Cai, Hongseok Namkoong, and Daniel Russo
    Under submission, 2025
  2. Bandit/RL Algorithms
    Impatient Bandits: Optimizing for the Long-Term Without Delay
    Kelly W Zhang, Thomas Baldwin-McDonald, Kamil Ciosek, Lucas Maystre, and Daniel Russo
    Under submission, 2025
  3. Statistical Inference
    Replicable Bandits for Digital Health Interventions
    Kelly W Zhang, Nowell Closser, Anna L. Trella, and Susan A. Murphy
    Minor revision at Statistical Science, 2025
  4. Bandit/RL Algorithms
    Active Exploration via Autoregressive Generation of Missing Data
    Tiffany (Tianhui) Cai, Hongseok Namkoong, Daniel Russo, and Kelly W Zhang
    Working paper; Selected for presentation at the Econometric Society Interdisciplinary Frontiers: Economics and AI+ML conference, 2024
  5. Bandit/RL Algorithms
    A Deployed Online Reinforcement Learning Algorithm In An Oral Health Clinical Trial
    Anna L Trella, Kelly W Zhang, Hinal Jajal, Inbal Nahum-Shani, Vivek Shetty, Finale Doshi-Velez, and Susan A Murphy
    Proceedings of the AAAI Conference on Artificial Intelligence (to appear), 2025
  6. Bandit/RL Algorithms
    Oralytics Reinforcement Learning Algorithm
    Anna L Trella, Kelly W Zhang, Stephanie M Carpenter, David Elashoff, Zara M Greer, Inbal Nahum-Shani, Dennis Ruenger, Vivek Shetty, Finale Doshi-Velez, and Susan A Murphy
    Technical report, 2024
  7. Bandit/RL Algorithms
    Monitoring Fidelity of Online Reinforcement Learning Algorithms in Clinical Trials
    Anna L Trella, Kelly W Zhang, Inbal Nahum-Shani, Vivek Shetty, Iris Yan, Finale Doshi-Velez, and Susan A Murphy
    Working paper, 2024
  8. Bandit/RL Algorithms
    The Fallacy of Minimizing Local Regret in the Sequential Task Setting
    Ziping Xu, Kelly W Zhang, and Susan Murphy
    Working paper, 2024
  9. Bandit/RL Algorithms
    Did we personalize? assessing personalization by an online reinforcement learning algorithm using resampling
    Susobhan Ghosh*, Raphael Kim*, Prasidh Chhabria, Raaz Dwivedi, Predrag Klasnja, Peng Liao, Kelly W Zhang, and Susan Murphy
    Machine Learning (Special Issue on Reinforcement Learning for Real Life), 2024
  10. Clinical Trials
    A mobile health intervention for emerging adults with regular cannabis use: A micro-randomized pilot trial design protocol
    Lara N. Coughlin, Maya Campbell, Tiffany Wheeler, Chavez Rodriguez, Autumn Florimbio, Susobhan Ghosh, Yongyi Guo, Pei-Yao Hung, Kelly W Zhang, Lauren Zimmerman, and 4 more authors
    Contemporary Clinical Trials, 2024
  11. Clinical Trials
    Optimizing an adaptive digital oral health intervention for promoting oral self-care behaviors: Micro-randomized trial protocol
    Inbal Nahum-Shani, Zara M Greer, Anna L Trella, Kelly W Zhang, Stephanie M Carpenter, Dennis Ruenger, David Elashoff, Susan A Murphy, and Vivek Shetty
    Contemporary Clinical Trials, 2024
  12. Statistical Inference
    Statistical Inference for Adaptive Experimentation
    Kelly W Zhang
    Thesis, 2023
  13. Bandit/RL Algorithms
    Reward design for an online reinforcement learning algorithm supporting oral self-care
    Anna L Trella, Kelly W Zhang, Inbal Nahum-Shani, Vivek Shetty, Finale Doshi-Velez, and Susan A Murphy
    Proceedings of the AAAI Conference on Artificial Intelligence, 2023
  14. Statistical Inference
    Statistical Inference after Adaptive Sampling for Longitudinal Data
    Kelly W Zhang, Lucas Janson, and Susan A Murphy
    Working paper, 2023
  15. Bandit/RL Algorithms
    Designing Reinforcement Learning Algorithms for Digital Interventions: Pre-Implementation Guidelines
    Anna L. Trella, Kelly W. Zhang, Inbal Nahum-Shani, Vivek Shetty, Finale Doshi-Velez, and Susan A. Murphy
    Algorithms (Special Issue Algorithms in Decision Support Systems); Preliminary version at RLDM 2022 (Multi-disciplinary Conference on RL and Decision Making); selected for an oral, 2022
  16. Statistical Inference
    Statistical Inference with M-Estimators on Adaptively Collected Data
    Kelly W Zhang, Lucas Janson, and Susan Murphy
    Advances in Neural Information Processing Systems (NeurIPS), 2021
  17. Statistical Inference
    Inference for Batched Bandits
    Kelly W Zhang, Lucas Janson, and Susan Murphy
    Advances in Neural Information Processing Systems (NeurIPS), 2020
  18. Bandit/RL Algorithms
    A bayesian approach to learning bandit structure in markov decision processes
    Kelly W Zhang, Omer Gottesman, and Finale Doshi-Velez
    Challenges of Real-World Reinforcement Learning 2020 (NeurIPS Workshop), 2020
  19. NLP
    Language modeling teaches you more syntax than translation does: Lessons learned through auxiliary task analysis
    Kelly W Zhang, and Samuel R Bowman
    BlackboxNLP 2018 (EMNLP Workshop), 2018
  20. NLP
    Adversarially Regularized Autoencoders
    Junbo (Jake) Zhao*, Yoon Kim*, Kelly Zhang, Alexander Rush, and Yann LeCun
    International Conference on Machine Learning (ICML), 2018