J
Ju Sun
Researcher at University of Minnesota
Publications - 69
Citations - 5839
Ju Sun is an academic researcher from University of Minnesota. The author has contributed to research in topics: Phase retrieval & Subspace topology. The author has an hindex of 23, co-authored 60 publications receiving 4857 citations. Previous affiliations of Ju Sun include National University of Singapore & SLAC National Accelerator Laboratory.
Papers
More filters
Journal ArticleDOI
Robust Recovery of Subspace Structures by Low-Rank Representation
TL;DR: It is shown that the convex program associated with LRR solves the subspace clustering problem in the following sense: When the data is clean, LRR exactly recovers the true subspace structures; when the data are contaminated by outliers, it is proved that under certain conditions LRR can exactly recover the row space of the original data.
Proceedings ArticleDOI
Hierarchical spatio-temporal context modeling for action recognition
TL;DR: This paper proposes to model the spatio-temporal context information in a hierarchical way, where three levels of context are exploited in ascending order of abstraction, and proposes to employ the Multiple Kernel Learning (MKL) technique to prune the kernels towards speedup in algorithm evaluation.
Journal ArticleDOI
A Geometric Analysis of Phase Retrieval
Ju Sun,Qing Qu,John Wright +2 more
TL;DR: It is proved that when the measurement vectors are generic, with high probability, a natural least-squares formulation for GPR has the following benign geometric structure: (1) There are no spurious local minimizers, and all global minimizers are equal to the target signal, up to a global phase, and (2) the objective function has a negative directional curvature around each saddle point.
Journal ArticleDOI
Complete Dictionary Recovery Over the Sphere I: Overview and the Geometric Picture
Ju Sun,Qing Qu,John Wright +2 more
TL;DR: The objective landscape is highly structured: with high probability, there are no "spurious" local minimizers; and around all saddle points the objective has a negative directional curvature, which makes the problem amenable to efficient optimization algorithms.
Journal ArticleDOI
A Geometric Analysis of Phase Retrieval
Ju Sun,Qing Qu,John Wright +2 more
TL;DR: In this paper, it was shown that when the measurement vectors are generic (i.i.d. complex Gaussian) and numerous enough, with high probability, a natural least-squares formulation for GPR has the following benign geometric structure: (1) there are no spurious local minimizers, and all global minimizers are equal to the target signal up to a global phase, and (2) the objective function has a negative directional curvature around each saddle point.