Open Positions
I will join the ECE Department at University of Rochester in 2025 as a tenure-track Assistant Professor. I am looking for self-motivated students (Ph.D., interns). Multiple fully funded Ph.D. positions are available starting from Fall 2025.
If you are interested, please fill out this form or contact me with your research interest, CV, transcripts, as well as writing samples (if any). In your email, please use the title "UR PhD Application: Your Name". For prospective Ph.D. students, check the instructions, apply to the UR ECE program, and mention my name in your application.About me
Research topics
My research goal is to develop optimization and learning theory for multi-objective and meta learning, especially under overparameterized settings with limited labeled data supervision, in order to better explain and predict the behavior of existing algorithms, to guide the design of principled, scalable and generalizable algorithms, and to apply to large-scale machine learning and signal processing problems.
Topics include but are not limited to:
Optimization: convergence analysis and scalable algorithm design for multi-objective and multi-level optimization (nonconvex, constrained, stochastic);
Learning theory for multi-objective/task/modal learning and meta learning (algorithm-dependent bounds, high-dimensional statistics, overparameterized / few-shot settings);
Applications to speech processing, computer vision, foundation model finetuning / alignment, multi-modal / distributed systems, trustworthy AI.
To prospective Ph.D. students
I welcome students from any STEM-related backgrounds (e.g., EE, CS, Math, Stats, Physics, other engineering / science background) to apply.
I hope you:
- are self-motivated, passionate about doing research;
- have good communication skills;
- are not afraid of tackling challenging problems.
The followings are preferred but not required:
- strong mathematical background and analytical skills;
- courses or research experience in machine learning / signal processing / optimization / learning theory;
- experience in programming.