Yudong Chen comes to UW-Madison Computer Sciences from a faculty position in the School of Operations Research and Information Engineering at Cornell University. He is researching and teaching in the area of machine learning, statistics, and optimization. Chen says that he likes “to build things that work but also to understand the mathematical principles behind why they work (and when they don’t).” He is excited to now have as colleagues many prominent researchers whom he has long respected.
Hometown: Guangzhou, China
Educational/professional background:
Associate Professor, School of Operations Research and Information Engineering, Cornell University, 2021
Assistant Professor, School of Operations Research and Information Engineering, Cornell University, 2015-2021
Postdoc, EECS, UC Berkeley, 2013-2015
Ph.D. in Electrical and Computer Engineering, University of Texas at Austin, 2013
How did you get into your field of research?
I like to build things that work but also to understand the mathematical principles behind why they work (and when they don’t). This drives me to my field of research, statistical and theoretical machine learning, where we design algorithms, apply them to interesting datasets/problems, and analyze their performance.
Could you please describe your area of focus?
My research lies in the intersection of machine learning, statistics, and optimization. I would say my research work is 70% theoretical and 30% computational. Some of the topics that I am interested in are the following: sparse recovery and compressed sensing, robust matrix completion and PCA, graph clustering and community detection in networks, mixture problems, computational and statistical tradeoffs, non-convex optimization, and reinforcement learning.
What main issue do you address or problem do you seek to solve in your work?
How to extract information from large, noisy datasets, efficiently and robustly, and use data to guide decision-making and system design?
What’s one thing you hope students who take a class with you will come away with?
Machine learning is fun, regardless of whether you are interested in theory, computation, or applications.
What attracted you to UW-Madison?
UW-Madison has a very strong group of faculty and students, across Computer Sciences, Engineering, Statistics, and Mathematics, in my field of research. In particular, UW-Madison has many prominent researchers who I respect and have a deep influence on my research career. Now they become my colleagues! Also, Madison is beautiful.
What was your first visit to campus like?
As we were driving off US-12/18 and saw Lake Monona, my wife exclaimed, “So beautiful!” Later that week my colleague Jerry Zhu took us on a tour of the Geology Museum. We were impressed by the awesome exhibits as well as how knowledgeable Jerry is.
What are you looking forward to doing or experiencing in Madison?
Things related to the lakes: canoe, kayak, row boat, paddle boat, stand-up paddle board, sail boat, skating/walking on the frozen lakes.
Please tell us about something you’re working on in layperson’s terms, so that non-computer scientists at UW-Madison and the general public can understand what you’re passionate about:
Computers can now beat the best human players in the game of Go. Not too long ago this was considered impossible, or at least beyond the reach of existing technology. Underlying this recent breakthrough are some exciting advances in machine learning and computational techniques. I’d like to better understand these techniques, improve upon them, and apply them to other interesting problems.
Hobbies/other interests:
Soccer, table tennis, watching movies