## Zhe Li
## About meI 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. ## NewsI 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## Research ExperienceMay 2017 - Nov 2017, Research Intern at Snap Research at Venice, CA May 2016 - Aug 2016, Research Intern at Yahoo Research at Sunnyvale, CA May 2015 - Aug 2015, Research Intern at General Motor Research at Warren, MI Aug 2014 - Present, Research Assistant at The University of Iowa at Iowa City, IA Aug 2011 - Jul 2013, Research Assistant at South Dakota State University at Brookings, SD Aug 2010 - Jun 2011, Research Assistant at Xi'an Jiaotong University at Xi'an, Shaanxi
## Recent PublicationsZhe Li, Xiaoyu Wang, Xutao Lv, Tianbao Yang,"SEP-Nets:Small and Effective Pattern Networks", [github][poster][slides][Media Coverage].
Tianbao Yang, Qihang Lin, Zhe Li, "Unified Convergence Analysis of Stochastic Momentum Methods for Convex and Non-convex Optimization", arxiv Preprint, arXiv: 1604.03257
Tianbao Yang, Zhe Li, Lijun Zhang, "A simple Analysis for Exp-concave Empirical Minimization with Arbitrary Convex Regularizer",AISTATS 2018. [pdf][poster][slides]
Yichi Xiao, Zhe Li, Tianbao Yang, and Lijun Zhang,"SVD-free Convex-Concave Approaches for Nuclear Norm Regularization", International Joint Conference on Artifical Intelligence (IJCAI), 2017. [supp][slides]
Zhe Li, Tianbao Yang, Lijun Zhang, and Rong Jin, "A Two-stage Approach for Learning a Sparse Model with Sharp Excess Risk Analysis",AAAI 2017 [pdf][Bibtex][poster][5-munutes-slides][15-minutes-slides]
Zhe Li, Boqing Gong, Tianbao Yang, "Improved Dropout for Shallow and Deep Learning", NIPS 2016. [pdf][Bibtex][poster][slides][5-minutes-vedio]
Zhe Li, Tianbao Yang, Lijun Zhang, Rong Jin, "Fast and Accurate Refined Nystrom based Kervel SVM", AAAI 2016. [pdf][Bibtex][poster][slides]
Zhe Li, Wei Wang, Sung Shin, Hyung D. Choi,"Enhanced Roughness Index for Breast Cancer Benign/Malignent Measurement Using Gaussian Mixture Model",In Proc. ACM Research in Applied Computation Symposium(RACS), Oct 2013
Byung K.Jung, Wei Wang, Zhe Li, Seong H. Son, Jung Yeop Kim, "A Sectorized Object Matching Approach for Breast Magnetic Resonance Image Similarity Study", In Proc. ACM Research in Applied Computation Symposium(RACS), Oct 2012
Zhe Li, Shin Sung, Soon I.Jeon, Seong H.Son, Jeong K. Pack, "A New Histogram-based Breast Cancer Image Classifier Using Gaussian Mixture Model", In Proc. ACM Research in Applied Computation Symposium(RACS), Oct 2012
## WorkshopZhe Li, Xiaoyu Wang, Xutao Lv, Tianbao Yang, "SEP-Nets: Small and Effective Pattern Networks". Beyond ISLVRC workshops 2017 Honululu, HIZhe 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
## Talks“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]
“Open the Magic Box of Deep Learning for Image Classification”[pdf] This 15-minutes talks trys to give prospective students interested in graduate program a sense of how powerful/magic deep neural network is and open this magic deep neural network box for them in 2016 Prospective Student Visit Day and Graduate Student Research Symposium.
“A Two-stage Approach for Learning a Sparse Model with sharp Excess Risk Analysis”[pdf]
“Nystrom Based Kernel Classification for Big Data”"[pdf]
## DemoObject Detection: This is C++ implementation of RCNN based on caffe framework, in which sliding window, bounding box regression are utilized.
## Honors and AwardsUIowa Graduate College Post-Comprehensive Research Award 2017 Neural Information Processing System (NIPS) Travel Award 2016 Outstanding Students Awards of Xi'an Jiaotong University 2010 BaoGang Outstanding Students Scholarship, XJTU 2009 National scholorship, XJTU 2008
## Professional ActivitiesProgram 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
## NotesThe following are some casual notes: |