Zheng XU 许正

xuzhustc AT gmail  [Curriculum Vitae][Google Scholar]

 Zheng's portrait

Welcome to Zheng's site! I am a graduate student of the department of Computer Science at the University of Maryland, College Park. I am currently working on optimization, machine learning and their applications, under the supervision of Dr.
 Tom Goldstein.

Previously, I was a Project Officer at Visual Computing Research Group, School of Computer EngineeringNanyang Technological University, Singapore. I worked on 
domain adaptation for computer vision, and also a collaborative project with Rolls-RoyceBefore joining NTU, I received my M.Eng. and B.Eng. in the Department of Electronic Engineering and Information Science, the University of Science and Technology of China (USTC), advised by Dr. Chang Wen Chen, Dr. Bin Liu and Dr. Houqiang Li. During my study as a master student, I was fortunate to take a long-term internship  at  Microsoft Research Asia (MSRA). I worked closely with Dr. Xin-Jing Wang on mining information from large-scale multimedia data. 


  • May 30 - Aug 25, intern with Honda research at Mountain View.
  • Aug 10, "Towards a Deeper Understanding of Training Quantized Neural Networks" won the best student paper in workshop Principled Approaches to Deep Learning@ICML, Sydney. Congrats to Hao, Soham and all co-authors.
  • Aug 5 - 10, travel to ICML@Sydney, present ACADMM for distributed optimization. Both my talk and poster are in Wed, Aug 9th. 
  • Jul 25, strange thing happens to my poster of ARADMM@CVPR. Hang it up in the morning and get lost in the afternoon. Sorry for guys who want to see it. Feel free to email me for discussion. Luckily I have a photo with the fancy fabric poster by my wife. I will miss it.
  • Jul 21-26, travel to CVPR@Honolulu, present Adaptive Relaxed ADMM, welcome to my poster on Tue Jul 25. 
  • Jul 21, a preliminary version of MATLAB code is released for ARADMM@CVPR. Feel free to have a try and email me your feedback!
  • May 12, "Adaptive Consensus ADMM for Distributed Optimization" has been accepted to ICML 2017,  many thanks to all coauthors.
  • Feb 13 - May 5, intern with Amazon AWS deep learning team, under the supervision of Dr. Anima Anandkumar; the internship is completed with a technical report on applying neural networks for the style transfer of natural language. 
  • Apr 20-22, travel to AISTATS, present Adaptive ADMM. Welcome to my poster on Apr 21 and presentation on Apr 22.
  • Mar 5, "Domain Generalization and Adaptation using Low Rank Exemplar SVMs" has been accepted to TPAMI, congrats Dr. Wen Li, and all coauthors.
  • Mar 3, "Adaptive Relaxed ADMM: Convergence Theory and Practical Implementation" has been accepted to CVPR 2017, many thanks to coauthors, Dr. Mario FigueiredoDr. Xiaoming Yuan, and Dr. Tom Goldstein.
  • Jan 24, "Adaptive ADMM with Spectral Penalty Parameter " has been accepted to AISTATS 2017 as oral presentation, many thanks to coauthors, Dr. Mario Figueiredo and Dr. Tom Goldstein.
  • Dec 4-10, travel to NIPS, present at two workshops about ADMM for nonconvex applications and tensor decomposition.