I am looking for Ph.D. students in the areas of signal & image processing (SIP), machine learning (ML), and numerical optimization. Some concrete directions include but not limited to:
- Mathematical foundations of deep learning: develop mathematical understandings of deep network through the lens of low-dimensional modelling (e.g., implicit regularizations, isometry properties, etc).
- Nonconvex optimization theory in SIP&ML: geometric analysis of optimization landscapes for (inverse) problems in signal processing and machine learning; design and analysis of large-scale nonconvex optimization algorithms.
- Applications in imaging sciences: design and implement fast optimization/machine learning algorithms for solving inverse problems in biomedical imaging and neuroscience.
The Ph.D. student can be co-advised with other senior faculty members in the SIP&ML area at Umich ECE. The successful candidate is expected to involve in one or two research directions listed above. Candidates with the following backgrounds are preferred:
- BS or above degrees in Electrical Engineering, Computer Science, Applied Math or other related fields, with passion in (machine learning) research.
- Either solid mathematical/signal processing background, or rich empirical experiences in deep learning.
- Publication in (top) machine learning conferences is preferred but not necessary.
Faculty Bio: Dr. Qu will be an assistant professor at Umich ECE starting from Jan. 2021. He received his B.E. degree from Tsinghua University in 2011, working with Prof. Yuantao Gu. He obtained his Ph.D. degree from Columbia University with Prof. John Wright in 2018, and worked as a Moore-Sloan fellow at NYU, Center for Data Science from 2018 to 2020. He is the recipient of the 2016 Microsoft Ph.D. Fellowship in machine learning, and publishes in top machine learning conferences such as NeurIPS, ICML, and ICLR. His current projects collaborate with Prof. Carlos Fernandez-Granda (NYU Courant), Prof. Yi Ma (UC Berkeley EECS), Prof. Zhihui Zhu (DU ECE), and Prof. Xiao Li (CUHK SZ). He has successfully mentored several students in the past (e.g. Yuexiang Zhai, MS@Columbia CS => PhD@UC Berkeley EECS; Xiao Li, PhD@CUHK EE => Faculty@CUHK SZ).
How to Apply
If you are interested, send your CV, transcripts, and any demonstration materials, such as papers or drafts to email@example.com with subject “[PhD application]”. Please apply by Dec. 15th following the instructions here and mention Dr. Qing Qu in the application (e.g., personal statement).
Some very good guidance for PhD students here, credited to Eric Gilbert.
Disclaimer: due to the high volume of incoming emails, your email might not be timely responded to (which I apologize in advance). However, I assure that I take a very close look at your background and contact you if there is a match of mutual interests.