Zhe Li

alt text 

PhD Candidate,
Department of Compute science,
The University of Iowa
317 MacLean Hall
Iowa city, IA 52246
Phone: 319-335-0713
Fax: 319-335-0627
E-post: zhe-li-1 [@] uiowa [DOT] edu

About me

I am currently a fifth year PhD student in Department of Computer science in The University of Iowa (Hawkeye), working with Prof. Tianbao Yang. I received my bachelor's degree and master's degree both in computer science from Xian Jiaotong University and South Dakota State University(Jackrabbits) in 2010 and 2013, respectively.


  • I will give a guest lecture on automatically searching the optimal neural network structures in deep learning course at The University of Iowa.

  • We gave a presentation on our oral AISTATS 2018 paper.

  • I gave a guest lecture on comressing deep neural networks in deep learning course at The University of Iowa.

Research Interest

alt text 

My research interests fall into three levels (as shown in the left figure):

  • understanding why machine can learn from learning theory perspective (statistical machine learning);

  • designing and analyzing optimization algorithms to facilate machine learning effeciently;

  • utilizing machine learning models(Specifically, deep neural network) to solve image classification, object detection or other computer vision task.

Research Experience

Recent Publications

  • Zhe Li, Tianbao Yang, Lijun Zhang, Rong Jin, "Fast and Accurate Refined Nystrom based Kervel SVM", AAAI 2016.


  • Zhe Li, Xiaoyu Wang, Xutao Lv, Tianbao Yang, "SEP-Nets: Small and Effective Pattern Networks".
    Beyond ISLVRC workshops 2017 Honululu, HI

  • Zhe Li, Tianbao Yang, Lijun Zhang, Rong Jin, "A Two-stage Approach for Learning a Sparse Model with Sharp Excess Risk Analysis"
    Learning Fast From Easy Data Workshop NIPS 2015, Montreal, Canada


  • “SEP-Nets: small and effective pattern networks” [pdf]

  • “Deep Learning With Caffe”[pdf], The University of Iowa, Apr 2017
    This lecture tried to teach students widely from The university of Iowa how to install caffe in the university cluster argon and how to train the very first deep neural network model for image classification using caffe. The installation in Argon clusteris quite tricky since students don't have root access to cluster. See Notes for detail information if you want to install caffe in your cluster environment.

  • “Improved Dropout for Shallow and Deep Learning”[pdf]

  • “A Two-stage Approach for Learning a Sparse Model with sharp Excess Risk Analysis”[pdf]

  • “Nystrom Based Kernel Classification for Big Data”"[pdf]


  • Object Detection: This is C++ implementation of RCNN based on caffe framework, in which sliding window, bounding box regression are utilized.

Honors and Awards

Professional Activities

  • Program Committee of The Twelfth Asia Information Retrieval Societies(AIRS) Conference 2016

  • Reviewer of The Thirtieth Annual Conference on Neural Information Processing Systems (NIPS) 2016

  • Reviewer of The Thirtieth AAAI Conference on Artificial Intelligence (AAAI) 2016

  • Reviewer of The 25th ACM International Conference on Information and Knowledge Management (CIKM) 2016

  • Reviewer of ACM Research in Applied Computation Symposium (RACS), 2012

  • Reviewer of The 13^th IEEE international Conference on Communication Systems 2012

  • Reviewer of International Conference on Wireless Communications and Signal Processing (WCSP), 2012

  • Reviewer of the 8^th IEEE International Conference on Wireless and Mobile Computing, Networking, and Communications(WiMob), 2012


The following are some casual notes: