SUN, Ruoyu

Associate Professor

Education Background

Ph.D. in Electrical and Computer Engineering, University of Minnesota, 2015
B.Sc. in Mathematics, Peking University, 2009

Research Field
Deep Learning Theory, Generative Models, Large-scale Optimization, Learning to Optimize, Graph Neural Nets, AI for Communication, Information Theory, Wireless Communications
Personal Website
Room 412, Daoyuan Building

Ruoyu Sun is currently an associate professor (tenured) in the School of Data Science at The Chinese University of Hong Kong, Shenzhen. From 2017 to 2022, he worked as an assistant professor (tenure-track) in the Department of ISE and ECE (affiliated), at the University of Illinois at Urbana-Champaign (UIUC). Prior to that, he was a full-time visiting research scientist at the Facebook AI Research (led by LeCun). He was a postdoctoral researcher at Stanford University. He obtained a Ph.D. in Electrical Engineering from the University of Minnesota, and B.S. in mathematics from Peking University. His research interests lie in machine learning, mathematical optimization, wireless communication and signal processing, etc. His specific research interests include deep learning theory and algorithms, generative models, large-scale optimization, learning to optimize, capacity theory and wireless network optimization. He has won the second place of INFORMS George Nicholson student paper competition, and honorable mention of INFORMS optimization society student paper competition. He published dozens of articles in machine learning conferences NeurIPS, ICML, ICLR, AISTATS, information theory and communication journals IEEE transaction on information theory, IEEE Signal Processing Magazine, Journal of Selected Areas in Communications, optimization journals Mathematical Programming, SIAM Journal on Optimization, Math of Operations Research, etc. He has been serving as an area chair of AI conferences NeurIPS, ICML, ICLR and AISTATS.

Academic Publications
  1. N. Shi, D. Li, M. Hong, R. Sun,RMSprop Converges with Proper Hyper-parameter”, ICLR (International Conference on Learning Representations) (Spotlight, 3.3% of 3000+ submissions),2021.
  2. R. Sun, T. Fang, A. Schwing,Towards a Better Global Loss Landscape of GANs”, NeurIPS (Annual Conference on Neural Information Processing System) (Oral, 1.1% of 9500+ submissions), 2020.
  3. D. Li, T. Ding, R. Sun, On the Benefit of Width for Neural Networks: Disappearance of Basins”, accepted to SIAM Journal on Optimization, 2022.
  4. S. Liang, R. Sun, R. Srikant,Revisiting Landscape Analysis in Deep Neural Networks: Eliminating Decreasing Paths to Infinity”, accepted to SIAM Journal on Optimization, 2021.
  5. R. Sun, D. Li, S. Liang, T. Ding, R. Srikant, “The Global Landscape of Neural Networks: An Overview”, IEEE Signal Processing Magazine, 2020.
  6. R. Sun, “Optimization for Deep Learning: an Overview”, Journal of Operations Research Society of China, 2020.
  7. R. Sun, Z.-Q. Luo, Y. Ye, "On the Efficiency of Random Permutation for ADMM and Coordinate Descent", Mathematics of Operations Research, 2019.
    Second Place, 2015 INFORMS George Nicholson Student Paper Competition.
  8. R. Sun, Z.-Q. Luo,Guaranteed Matrix Completion via Nonconvex Factorization, IEEE Transaction on Information Theory, 2016.
    --A shorter version appeared at IEEE FOCS (IEEE Annual Symposium on Foundations of Computer Science) 2015.
    --Honorable mention, 2015 INFORMS Optimization Society student paper prize.