Canyi Lu

mailto:canyilu AT gmail.com


Carnegie Mellon University

Personal Site


I am currently a Postdoctoral Research Associate at Carnegie Mellon University. I obtained my phd degree from the National University of Singapore, working closely with Profs. Jiashi Feng, Shuicheng Yan and Zhouchen Lin.


  • Statistical Learning of Structured Sparsity
  • Optimization
  • Computer Vision


  • Ph.D. in Machine Learning, 2013-2017

    National University of Singapore

  • Msc in Electronic Information and Engineering, 2009-2012

    University of Science and Technology of China

Curriculum Vitae


Postdoc Research Associate

Carnegie Mellon University

Dec 2017 – Present Pittsburgh, US

Visiting Student

Priceton Univeristy

Aug 2016 – Nov 2016 Priceton, US


Microsoft Asia

Aug 2015 – Oct 2015 Beijing

Research Assistant

National University of Singapore

Sep 2012 – Jul 2013 Singapore

Visiting Student

Peking Univeristy

Aug 2012 – Jun 2013 Beijing

Publications @ZERO Lab

Subspace Clustering by Block Diagonal Representation. TPAMI, 2019.

In this work, we first consider a general formulation and provide a unified theoretical guarantee of the block diagonal property of the …

Tensor Robust Principal Component Analysis with A New Tensor Nuclear Norm. PAMI, 2018.

In this paper, we consider the Tensor Robust Principal Component Analysis (TRPCA) problem, which aims to exactly recover the low-rank …

Tensor Factorization for Low-Rank Tensor Completion. TIP, 2018.

We propose a novel low-rank tensor factorization method for efficiently solving the 3-way tensor completion problem.

Exact Low Tubal Rank Tensor Recovery from Gaussian Measurements. IJCAI, 2018.

With a careful choice of the atomic set, we prove that TNN is a special atomic norm.

Nonconvex Sparse Spectral Clustering by Alternating Direction Method of Multipliers. AAAI, 2018.

We propose an efficient Alternating Direction Method of Multipliers (ADMM) to solve the nonconvex SSC and provide the convergence …

Optimized Projections for Compressed Sensing via Direct Mutual Coherence Minimization. SP, 2018.

We propose to find an optimal projection matrix by minimizing the mutual coherence of PD directly to recover the signal from a small …

A Unified Alternating Direction Method of Multipliers by Majorization Minimization. TPAMI, 2018.

We respectively present the unified frameworks of Gauss-Seidel ADMMs and Jacobian ADMMs, which use different historical information for …

Tensor Robust Principal Component Analysis: Exact Recovery of Corrupted Low-Rank Tensors via Convex Optimization. CVPR, 2016.

This paper studies the Tensor Robust Principal Component (TRPCA) problem which extends the known Robust PCA to the tensor case.

Convex Sparse Spectral Clustering: Single-view to Multi-view. TIP, 2016.

We propose a novel convex relaxation of SSC based on the convex hull of the fixed rank projection matrices.

Fast Proximal Linearized Alternating Direction Method of Multiplier with Parallel Splitting. AAAI, 2016.

We propose the Fast Proximal Augmented Lagragian Method (Fast PALM) which achieves the convergence rate O(1/K^2), compared with O(1/K) …

Academic Acativities

Reviewer to Journals

Chair/Reviewer to Conferences


Best Poster Award, 1st Place,

Chinese Government Award for Outstanding Self-Financed Students Abroad

Stars of Tomorrow

Microsoft Research Asia Fellowship

Travel Grant

Outstanding Postgraduate Award

Excellent Bachelor Dissertation Award

National Scholarship for Encouragement

National Scholarship (2 times)

Excellent Student Scholarship (7 times)