About me
I am a final-year Ph.D. candidate in Statistics at Purdue University, where I am fortunate to be coadvised by Prof. Qifan Song and Prof. Jean Honorio. I received an M.S. in Computer Science and Statistics during my Ph.D. study. I received an B.Sc. in Mathematics at the Chinese University of Hong Kong. I have interned at several industrial companies including Meta AI, Amazon Ads, and Sensetime Research.
My research interests include:
- Optimization Theory
- Bandit Algorithms
- Federated Learning
- High Dimensional Statistics
- Deep Learning Theory and Practice
I am actively building and maintaining an open-source Python library for X-armed bandit algorithms and benchmarks. Check out this repository.
Research collaborations from both industry and academia are highly welcomed. If you are interested in optimization/bandit/federated learning-related topics, feel free to reach out to me.
Recent News
- [May, 2023]. I will be an Research Scientist Intern at Meta this summer!
- [Jan, 2023]. Our team has recently launched the PyXAB project. Take a look! .
- [Jul, 2022]. "Variance Reduction on General Adaptive Mirror Descent" is accepted by the Machine Learning Journal!
- [May, 2022]. "A Simple Unified Framework for High Dimensional Bandit Problems" is accepted by ICML2022!
- [Apr, 2022]. I will be an Applied Scientist Intern at Amazon this summer!
- [Mar, 2022]. I have passed the preliminary exam! Many thanks to my advisors and my committee members.
- [Oct, 2021]. "Optimum-statistical Collaboration Towards Efficient Black-box Optimization" is accepted by the NeurIPS2021 OPT Workshop!
- [Oct, 2020]. "Variance Reduction on Adaptive Mirror Descent" is accepted by the NeurIPS2020 OPT Workshop with Spotlight presentation!
- [Aug, 2020]. I have passed the qualifying exams!