
NCVX: A UserFriendly and Scalable Package for Nonconvex Optimization in Machine Learning
Optimizing nonconvex (NCVX) problems, especially those nonsmooth (NSMT) ...
read it

SelfValidation: Early Stopping for SingleInstance Deep Generative Priors
Recent works have shown the surprising effectiveness of deep generative ...
read it

Rethink Transfer Learning in Medical Image Classification
Transfer learning (TL) with deep convolutional neural networks (DCNNs) h...
read it

Phase Retrieval using SingleInstance Deep Generative Prior
Several deep learning methods for phase retrieval exist, but most of the...
read it

A Prospective Observational Study to Investigate Performance of a Chest Xray Artificial Intelligence Diagnostic Support Tool Across 12 U.S. Hospitals
Importance: An artificial intelligence (AI)based model to predict COVID...
read it

Towards LowPhoton Nanoscale Imaging: Holographic Phase Retrieval via Maximum Likelihood Optimization
A new algorithmic framework is presented for holographic phase retrieval...
read it

Inverse Problems, Deep Learning, and Symmetry Breaking
In many physical systems, inputs related by intrinsic system symmetries ...
read it

DualReference Design for Holographic Coherent Diffraction Imaging
A new reference design is introduced for Holographic Coherent Diffractio...
read it

Holographic Phase Retrieval and Optimal Reference Design
A general mathematical framework and recovery algorithm is presented for...
read it

Subgradient Descent Learns Orthogonal Dictionaries
This paper concerns dictionary learning, i.e., sparse coding, a fundamen...
read it

Weighted AdaGrad with Unified Momentum
Integrating adaptive learning rate and momentum techniques into SGD lead...
read it

A Local Analysis of Block Coordinate Descent for Gaussian Phase Retrieval
While convergence of the Alternating Direction Method of Multipliers (AD...
read it

A Geometric Analysis of Phase Retrieval
Can we recover a complex signal from its Fourier magnitudes? More genera...
read it

Complete Dictionary Recovery over the Sphere II: Recovery by Riemannian Trustregion Method
We consider the problem of recovering a complete (i.e., square and inver...
read it

Complete Dictionary Recovery over the Sphere I: Overview and the Geometric Picture
We consider the problem of recovering a complete (i.e., square and inver...
read it

When Are Nonconvex Problems Not Scary?
In this note, we focus on smooth nonconvex optimization problems that ob...
read it

Complete Dictionary Recovery over the Sphere
We consider the problem of recovering a complete (i.e., square and inver...
read it

Finding a sparse vector in a subspace: Linear sparsity using alternating directions
Is it possible to find the sparsest vector (direction) in a generic subs...
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

ClosedForm Solutions to A Category of Nuclear Norm Minimization Problems
It is an efficient and effective strategy to utilize the nuclear norm ap...
read it

Selective Image SuperResolution
In this paper we propose a vision system that performs image Super Resol...
read it

Robust Recovery of Subspace Structures by LowRank Representation
In this work we address the subspace recovery problem. Given a set of da...
read it

Robust LowRank Subspace Segmentation with Semidefinite Guarantees
Recently there is a line of research work proposing to employ Spectral C...
read it
Ju Sun
is this you? claim profile
Postdoctoral Scholar, Department of Mathematics at Stanford University