Dejiao Zhang

I'm a PhD candidate at the University of Michigan in the Electrical Engineering and Computer Science department. My Advisor is Prof. Laura Balzano. My research mainly focuses on Grassmannian optimization, convergence theory for non-convex problems, compressed sensing, and deep learning. For a list of my publications, see below or check out my Google Scholar Profile.

 

Contact Me:

Publications

 

Working Paper

  • Adaptive Parameters Tying for Neural Network.

 

Preprints

  • Dejiao Zhang, Laura Balzano. Convergence of a Grassmannian Gradient Descent Algorithm for Subspace Estimation from Undersampled Data. Submitted to IEEE transactions on Information Theory. (pdf)

 

Journal

  • Jun He, Dejiao Zhang, Laura Balzano, Tao Tao. Iterative Grassmannian Optimization for Robust Image Alignment. Journal of Image and Vision Computing, 2014. (pdf)

 

Conference

  • Dejiao Zhang, Laura Balzano. Convergence Results of GROUSE. Accepted by the Signal Processing with Adaptive Sparse Structured Representations (SPARS) workshop, 2017. (pdf)
  • Dejiao Zhang, Laura Balzano. Matched Subspace Detection Using Compressively Sampled Data. Accepted by the 42nd IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2017. (pdf)
  • Dejiao Zhang, Laura Balzano. Global Convergence of a Grassmannian Gradient Descent Algorithm for Subspace Estimation. In Proceedings of the 19th International Conference on Artificial Intelligence and Statistics (AISTATS), 2016. (pdf)
  • Jun He, Dejiao Zhang, Laura Balzano, Tao Tao. Iterative Online Subspace Learning for Robust Image Alignment. In IEEE Automatic Face and Gesture Recognition Conference (FG), 2013. (pdf)