
Lowrank matrix recovery with nonquadratic loss: projected gradient method and regularity projection oracle
Existing results for lowrank matrix recovery largely focus on quadratic...
read it

From Symmetry to Geometry: Tractable Nonconvex Problems
As science and engineering have become increasingly datadriven, the rol...
read it

Structures of Spurious Local Minima in kmeans
kmeans clustering is a fundamental problem in unsupervised learning. Th...
read it

Polynomial Matrix Completion for Missing Data Imputation and Transductive Learning
This paper develops new methods to recover the missing entries of a high...
read it

Analysis of the Optimization Landscapes for Overcomplete Representation Learning
We study nonconvex optimization landscapes for learning overcomplete rep...
read it

ShortandSparse Deconvolution  A Geometric Approach
Shortandsparse deconvolution (SaSD) is the problem of extracting local...
read it

Global Convergence of Least Squares EM for Demixing Two LogConcave Densities
This work studies the location estimation problem for a mixture of two r...
read it

Highdimensional semisupervised learning: in search for optimal inference of the mean
We provide a highdimensional semisupervised inference framework focuse...
read it

On the Global Geometry of SphereConstrained Sparse Blind Deconvolution
Blind deconvolution is the problem of recovering a convolutional kernel ...
read it

Geometry and Symmetry in ShortandSparse Deconvolution
We study the ShortandSparse (SaS) deconvolution problem of recovering ...
read it

Structured Local Optima in Sparse Blind Deconvolution
Blind deconvolution is a ubiquitous problem of recovering two unknown si...
read it

Convolutional Phase Retrieval via Gradient Descent
We study the convolutional phase retrieval problem, which considers reco...
read it

Scalable Robust Matrix Recovery: FrankWolfe Meets Proximal Methods
Recovering matrices from compressive and grossly corrupted observations ...
read it

Toward Guaranteed Illumination Models for NonConvex Objects
Illumination variation remains a central challenge in object detection a...
read it

Efficient PointtoSubspace Query in ℓ^1: Theory and Applications in Computer Vision
Motivated by vision tasks such as robust face and object recognition, we...
read it

Efficient PointtoSubspace Query in ℓ^1 with Application to Robust Object Instance Recognition
Motivated by vision tasks such as robust face and object recognition, we...
read it
Yuqian Zhang
is this you? claim profile