Research
My research strives to develop efficient, scalable and trustworthy machine learning algorithms to build intelligent learning-enabled networked systems. Towards this goal, I use theoretical tools from machine learning, optimization, and probability, to design rigorous algorithms with provable guarantees that have been deployed in data networks, edge/mobile/cloud computing systems, social networks, and beyond.
I am on the 2023-2024 job market looking for faculty positions. My CV can be found here.
Bio
I am a joint postdoc at Caltech and UMass Amherst, working with Prof. Adam Wierman and Prof. Mohammad Hajiesmaili. I recevied my Ph.D. degree in Electrical and Computer Engineering from Carnegie Mellon University in 2022. I was a member of the LIONS research group advised by Prof. Carlee Joe-Wong. Before that, I received my B.E. in Communication Engineering from Nanjing University of Posts and Telecommunications in 2017.
News
- Dec. 2023: Two papers about split learning on the mobile edge and context-aware probabilistic maximum coverage bandits are accepted to INFOCOM 2024.
- Oct. 2023: Our work on online pause and resume for carbon-aware load shifting is accepted to SIGMETRICS 2024.
- Sept. 2023: Our work on adversarial attacks on online learning to rank is accepted to NeurIPS 2023.
- June 2023: Our work on intelligent communication planning for constrained environmental IoT sensing is accepted to SECON 2023.
- Apr. 2023: Our work on contextual combinatorial bandits with probabilistically triggered arms is accepted to ICML 2023.
- Feb. 2023: I give a talk on variance-adaptive bandit algorithms in the Information Theory and Applications (ITA) Workshop.
Honors and Awards
- CDS Postdoctoral Fellowship, UMass Amherst CICS 2022
- SIGMETRICS Best Poster Award 2022
- Qualcomm Innovation Fellowship Finalist 2021
- AAAI-20 Student Scholarship 2020
- SIGMETRICS Student Travel Grant 2018
- Carnegie Institute of Technology Dean’s Fellowship 2017
- National Scholarship from Ministry of Education of China 2015, 2016