scispace - formally typeset
R

Richard Zhang

Researcher at Adobe Systems

Publications -  121
Citations -  18522

Richard Zhang is an academic researcher from Adobe Systems. The author has contributed to research in topics: Optimization problem & Computer science. The author has an hindex of 26, co-authored 114 publications receiving 10747 citations. Previous affiliations of Richard Zhang include University of California & University of Illinois at Urbana–Champaign.

Papers
More filters
Proceedings Article

How Much Restricted Isometry is Needed In Nonconvex Matrix Recovery

TL;DR: It is shown that moderate RIP is not enough to eliminate spurious local minima, so existing results can only hold for near-perfect RIP, and arguments based solely on norm preservation will only be applicable to a narrow set of nearly-isotropic instances.
Posted Content

How Much Restricted Isometry is Needed In Nonconvex Matrix Recovery

TL;DR: In this article, the authors show that moderate RIP is not enough to eliminate spurious local minima, so existing results can only hold for near-perfect RIP, and they prove that every x is the spurious local minimum of a rank-1 instance of matrix recovery that satisfies RIP.
Journal ArticleDOI

RadMAP: The Radiological Multi-sensor Analysis Platform

TL;DR: The Radiological Multi-sensor Analysis Platform (RadMAP) as mentioned in this paper is designed to allow the systematic study of natural radiological background variations and to serve as a development platform for emerging concepts in mobile radiation detection and imaging.