Yingzhen Yang

About me

I am a research scientist in machine learning at Snap Research.

Research Interests

My research focuses on machine learning and deep learning, and I am interested in the combination of conventional statistical machine learning and deep learning so as to design understandable architecure for deep learning. My research covers theory and application of deep learning including model compression and generalziation, subspace learning, manifold learning, sparse representation and compressive sensing, nonparametric models, probabilistic graphical models and generalization analysis of classification, semi-supervised learning and clustering; I also deveote efforts to optimization theory for important optimization problems involved in my research, especially for sparse regression problems and the optimizatino of deep learning.

In my early years I also conducted research on computer vision and computer graphics. Click to see the details

View more details in my CV and research statement:

Research Statement


2323 Beckman Institute, 405 N. Mathews Ave.
Urbana, IL, 61801
Phone: (412) 508-5664
Email: yyang58 -AT- illinois.edu

Honors and Awards

2016 ICML Scholarship (Travel Award)
2016 ECCV Best Paper Finalist (among 11 out of all submissions)
2012 AAAI Scholarship
2010 Carnegie Institute of Technology Dean's Tuition Fellowship
2009 "Lu Zeng Yong" CAD&CG High-Tech Award(for six researchers in China who have made distinguished achievements in Computer-Aided Design&Computer Graphics)
Before 2005: Bronze medal in National Senior High School Mathematics Competition, First Prize of National Junior High School Mathematics Competition

Professional Services & Activities

Program Committee Member: International Joint Conferences on Artificial Intelligence (IJCAI) 2015, IJCAI 2017, IJCAI 2018, IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2018
Reviewer: Journal of Machine Learning Research (JMLR), IEEE Transactions on Image Processing (TIP), Pattern Recognition (PR), Knowledge and Information Systems (KAIS), Machine Vision and Applications (Springer Journal)
Reviewer and Organizer: ACM Multimedia Workshop on Surreal Media and Virtual Cloning, in conjunction with ACM Multimedia 2010

Industrial Experience

Ten years of experience in C/C++ programming and software design.

Research Intern, Microsoft Research at Redmond, WA. May 2015 to Aug. 2015. online probabilistic topic models for large-scale application with CUDA C/C++ programming.
Research Intern, Microsoft Research at Redmond, WA. May 2014 to Aug. 2014. Developed parallelized and accelerated probabilistic topic models with CUDA C/C++ programming.
Research Intern, Hewlett-Packard Labs, Palo Alto, California. May 2011 to Aug. 2011. Efficient markerless augmented reality with C/C++ programming.


Please refer to the details of my projects here.

Recent Publications (Full List)

Yingzhen Yang.
Dimensionality Reduced L0-Sparse Subspace Clustering.
Proc. of International Conference on Artificial Intelligence and Statistics (AISTATS) 2018.

Yingzhen Yang, Jiashi Feng, Jiahui Yu, Jianchao Yang, Pushmeet Kohli, Thomas S. Huang.
Neighborhood Regularized L1-Graph.
Proc. of Conference on Uncertainty in Artificial Intelligence (UAI) 2017. [Paper]

Yingzhen Yang, Jiahui Yu, Pushmeet Kohli, Jianchao Yang, Thomas S. Huang.
Support Regularized Sparse Coding and Its Fast Encoder.
Proc. of International Conference on Learning Representations (ICLR) 2017. [Paper]

Yingzhen Yang, Jiashi Feng, Nebojsa Jojic, Jianchao Yang, Thomas S. Huang.
L0-Sparse Subspace Clustering.
Proc. of European Conference on Computer Vision (ECCV) 2016. (Oral Presentation, Among 11 Best Paper Candidates) [Paper] [Supplementary] [Slides] [Code (Both CUDA C++ for extreme efficiency and MATLAB)]
Our work establishs almost surely equivalence between L0 sparsity and subspace detection property, under the mild condition of i.i.d. data generation and nondegenerate distribution. This is much milder than previous conditions required by L1 sparse subspace clustering literature. Click to see the key points in the talk

Yingzhen Yang, Zhangyang Wang, Zhaowen Wang, Shiyu Chang, Ding. Liu, Honghui Shi, Thomas S. Huang.
Epitomic Image Super-Resolution.
Proc. of AAAI Conference on Artificial Intelligence (AAAI) 2016 (Best Poster/Best Presentation Finalist for Student Poster Program). [Project&Code]