Current Students and Postdocs
Postdocs
Ph.D. Students
- Luke Francisco, Biomedical Informatics and Data Science Training Program (BIDS-TP) Fellow: Mobile Health, Missing Data, Synthetic Data Generation
- Kihyuk (Ki) Hong: Reinforcement Learning
- Chinmaya Kausik: Offline Reinforcement Learning (co-advised with Prof. Martin Strauss)
- Preetham Mohan: Quantum Learning Theory (co-advised with Prof. Shravan Veerapaneni)
- Gang Qiao: Pure Exploration
- Vinod Raman, NSF Graduate Research Fellow: Boosting, Privacy, Adversarial Robustness, Distributed Learning
- Saptarshi Roy: High dimensional statistics (co-advised with Prof. Ziwei Zhu)
- Ziping Xu, Rackham Predoctoral Fellow: Reinforcement Learning, Transfer Learning, Multitask Learning, Curriculum Learning
In addition to the above students, I am also working with the following Ph.D. students on an experimental basis:
- Yash Patel: Conformer Generation, Cryo-EM
- Eduardo Ochoa Rivera: Machine Learning for Detection and Characterization of Microplastics
- Unique Subedi: Learnability of Vector-valued Functions
- Jacob (Jake) Trauger: Graph Kernels, Graph Neural Networks, Machine Olfaction
Master's students
- Zehua Wang: New Computational Approches for Best Subset Selection (co-mentored with Saptarshi Roy)
Undergraduate Students
- Kevin Cao: Protein Reconstruction from Cryo-EM (co-mentored with Yash Patel)
- Andy Gu: Mobile Health (co-mentored with Luke Francisco)
- Yuhang Li: Reinforcement Learning (co-mentored with Kihyuk Hong)
- Rui Nie: Machine Olfaction (co-mentored with Jake Trauger)
- Kevin Tan: Offline RL (co-mentored with Chinmaya Kausik)
- Manheng Wang: High dimensional statistics (co-mentored with Saptarshi Roy)
- Oliver Wu: Mobile Health (co-mentored with Luke Francisco)
- Heyi Xu: Machine Learning for Microplastics (co-mentored with Eduardo Ochoa Rivera)
- Zhong Zheng: Protein Reconstruction from Cryo-EM (co-mentored with Yash Patel)
Former Students and Postdocs
Postdocs
Ph.D. Students
- Laura Niss, Ph.D. 2022. Thesis: Topics in Sequential Decision Making and Algorithmic Fairness (co-advised with Prof. Yuekai Sun).
- Aditya Modi, Ph.D. 2021. Thesis: Provably Efficient Reinforcement Learning Under Linear Model Structures: From Tabular to Feature Based Exploration (co-advised with Prof. Satinder Singh). ML Research Scientist, Microsoft, Sunnyvale, CA.
- Baekjin Kim, Ph.D. 2021, Department of Statistics Outstanding Dissertation Award. Thesis: Stability in Online Learning: From Random Perturbations in Bandit Problems to Differential Privacy. Machine Learning Engineer, Twitter, San Francisco, CA.
- Jonathan (Jack) Goetz, Ph.D. 2020. Thesis: Active Learning in Non-parametric and Federated Settings. Research Scientist, Facebook, Menlo Park, CA.
- Young Hun Jung, Ph.D. 2020. Thesis: New Directions in Online Learning: Boosting, Partial Information, and Non-Stationarity. ML Research Scientist, Microsoft, Sunnyvale, CA.
- Yitong Sun, Ph.D. 2019, ProQuest Distinguished Dissertation Awards Honorable Mention, Peter Smereka Award for Best AIM (Applied and Interdisciplinary Mathematics) Thesis: Random Features Methods in Supervised Learning (co-advised with Prof. Anna Gilbert). Research Engineer, Huawei, Shenzhen, China.
- Chansoo Lee, Ph.D. 2018. Thesis: Analysis of Perturbation Techniques in Online Learning (co-advised with Prof. Jacob Abernethy). Software Engineer, Google Brain, Pittsburgh, PA.
- Kam Chung Wong, Ph.D. 2017. Thesis: Lasso Guarantees for Dependent Data. Advisory Services Senior, Ernst and Young, New York, NY.
- Mohamad Kazem Shirani Faradonbeh, Ph.D. 2017. Thesis: Non-asymptotic Adaptive Control of Linear-Quadratic Systems (co-advised with Prof. George Michailidis). Assistant Professor, Department of Statistics, University of Georgia, Athens, GA.
- Huitian (Emmy) Lei, Ph.D. 2016. Thesis: An Online Actor Critic Algorithm and a Statistical Decision Procedure for Personalizing Intervention (co-advised with Prof. Susan Murphy). Senior Data Scientist, Lyft, San Francisco, CA.
- Sougata Chaudhuri, Ph.D. 2016. Thesis: Learning to Rank: Online Learning, Statistical Theory and Applications. Senior Machine Learning Scientist, DoorDash, Mountain View, CA.
Master's students
- Chengcheng Wang (2022): Machine Learning for Detection and Characterization of Microplastics (co-mentored with Eduardo Ochoa Rivera)
- Shubham Pandey (2022): Conformer Generation (co-mentored with Yash Patel)
- Pengfei Liu (2022): Adversarial Bandits, Follow the Perturbed Leader
- Ziteng Pang (2020-2022): Machine Olfaction, Graph Neural Networks
- Alex Shen (2020-2022): Federated Learning and Differential Privacy for Mobile Health
- Anthony DiGiovanni (2019-2021): Multi-Agent Reinforcement Learning
- Aravind Mantravadi (2020-2021): Machine Olfaction
- Tarun Gogineni (2019-2020): Applications of Reinforcement Learning in Computational Chemistry (co-mentored with Prof. Paul Zimmerman)
- Jessica Liu (2018-2020): Federated Learning for Mobile Health
- Mengjie Shi (2018-2019): Mood Prediction Using Data from Smartphones and Wearables
- Jin Seok (Andy) Lee (2014-2017): HeartSteps and NIDA challenge "Addiction Research: There's an app for that" (co-mentored with Profs. Predrag Klasnja and Susan Murphy)
- Anurag Beniwal (2015-2016): Learning Analytics
- Vatshank Chaturvedi (2014-2015): Matching Algorithms on Random Graphs
Undergraduate Students with Honors Thesis
Other Undergraduate Students
- Chengsong Zhang (2022): Conformer Generation (co-mentored with Yash Patel)
- Runxuan Jiang (2019-2022): Conformer Generation, Curriculum Learning for Reinforcement Learning (co-mentored with Ziping Xu)
- Alexander (Alex) Netzley (2022): Conformer Generation (co-mentored with Yash Patel)
- Rahul Gupta (2022): Curriculum Learning for Reinforcement Learning (co-mentored with Ziping Xu)
- Zhiyu (Ted) Yuan (2022): Curriculum Learning for Reinforcement Learning (co-mentored with Ziping Xu)
- Zhong Zheng (2022): Algorithmic fairness (co-mentored with Laura Niss)
- Ruoyu Wang (2022): Algorithmic fairness (co-mentored with Laura Niss)
- Yunze Wei (2022): Conformer Generation (co-mentored with Yash Patel)
- Mohamad Bairakdar (2019-2021): Machine Learning in Aging Research (co-mentored with Matthias Truttman)
- Anh Tuan (Alan) Tran (2020-2021): Reinforcement Learning (co-mentored with Ziping Xu)
- Yifei He (2020-2021): Reinforcement Learning for Conformer Generation
- Zhongqi (Kevin) Ma (2020-2021): AI in education (co-mentored with Laura Niss)
- Zhihao (Patrick) Su (2020-2021): AI in education (co-mentored with Laura Niss)
- Vinod Raman (2020-2021): Online Boosting with Partial Feedback
- Alexandria (Alex) Pawlik (2019-2020): Privacy of Contact Tracing (co-mentored with Baekjin Kim)
- Haonan Sun (2019-2020): Learning Analytics (co-mentored with Laura Niss)
- Tarun Gogineni (2019): Active Learning (co-mentored with Jonathan (Jack) Goetz)
- Yeqing Lin (2019): Active Learning (co-mentored with Jonathan (Jack) Goetz)
- Daniel Zhang (2017-2019): Online Boosting (co-mentored with Young Hun Jung)
- Michael Kovalcik (2015-2017): Mobile Health (co-mentored with Prof. Susan Murphy)
- Joshua Song (2016): NIDA challenge "Addiction Research: There's an app for that" (co-mentored with Prof. Predrag Klasnja, Prof. Susan Murphy, and Prof. Maureen Walton)
- Steven Zheng (2016): NIDA challenge "Addiction Research: There's an app for that" (co-mentored with Prof. Predrag Klasnja, Prof. Susan Murphy, and Prof. Maureen Walton)
- Cyrus Anderson (2014-2015): Development of HeartSteps, a mobile phone app for encouraging physical activity (co-mentored with Prof. Predrag Klasnja)
- Ning Niu (2015): Improving importance weighted active learning (co-mentored with Prof. Barzan Mozafari)
- Scott Bommarito (2013-2014): Development of a pilot version of an Android app for mobile health; Simulations with bandit learning algorithms
- Bingjie Xu (2013): Development of a pilot version of an Android app for mobile health