Network


Latest external collaboration on country level. Dive into details by clicking on the dots.

Hotspot


Dive into the research topics where Richard Y. Chen is active.

Publication


Featured researches published by Richard Y. Chen.


Annals of Probability | 2014

Matrix Concentration Inequalities via the Method of Exchangeable Pairs

Lester W. Mackey; Michael I. Jordan; Richard Y. Chen; Brendan Farrell; Joel A. Tropp

This paper derives exponential concentration inequalities and polynomial moment inequalities for the spectral norm of a random matrix. The analysis requires a matrix extension of the scalar concentration theory developed by Sourav Chatterjee using Stein’s method of exchangeable pairs. When applied to a sum of independent random matrices, this approach yields matrix generalizations of the classical inequalities due to Hoeffding, Bernstein, Khintchine and Rosenthal. The same technique delivers bounds for sums of dependent random matrices and more general matrix-valued functions of dependent random variables.


New Journal of Physics | 2015

Solving ptychography with a convex relaxation

Roarke Horstmeyer; Richard Y. Chen; Xiaoze Ou; Brendan P. W. Ames; Joel A. Tropp; Changhuei Yang

Ptychography is a powerful computational imaging technique that transforms a collection of low-resolution images into a high-resolution sample reconstruction. Unfortunately, algorithms that currently solve this reconstruction problem lack stability, robustness, and theoretical guarantees. Recently, convex optimization algorithms have improved the accuracy and reliability of several related reconstruction efforts. This paper proposes a convex formulation of the ptychography problem. This formulation has no local minima, it can be solved using a wide range of algorithms, it can incorporate appropriate noise models, and it can include multiple a priori constraints. The paper considers a specific algorithm, based on low-rank factorization, whose runtime and memory usage are near-linear in the size of the output image. Experiments demonstrate that this approach offers a 25% lower background variance on average than alternating projections, the ptychographic reconstruction algorithm that is currently in widespread use.


Optics Express | 2012

Markov speckle for efficient random bit generation

Roarke Horstmeyer; Richard Y. Chen; Benjamin Judkewitz; Changhuei Yang

Optical speckle is commonly observed in measurements using coherent radiation. While lacking experimental validation, previous work has often assumed that speckles random spatial pattern follows a Markov process. Here, we present a derivation and experimental confirmation of conditions under which this assumption holds true. We demonstrate that a detected speckle field can be designed to obey the first-order Markov property by using a Cauchy attenuation mask to modulate scattered light. Creating Markov speckle enables the development of more accurate and efficient image post-processing algorithms, with applications including improved de-noising, segmentation and super-resolution. To show its versatility, we use the Cauchy mask to maximize the entropy of a detected speckle field with fixed average speckle size, allowing cryptographic applications to extract a maximum number of useful random bits from speckle images.


arXiv: Probability | 2012

The masked sample covariance estimator: an analysis using matrix concentration inequalities

Richard Y. Chen; Alex Gittens; Joel A. Tropp


Electronic Journal of Probability | 2014

Subadditivity of matrix phi-entropy and concentration of random matrices

Joel A. Tropp; Richard Y. Chen


arXiv: Computer Vision and Pattern Recognition | 2017

Convolutional neural networks that teach microscopes how to image.

Roarke Horstmeyer; Richard Y. Chen; Barbara Kappes; Benjamin Judkewitz


arXiv: Computer Vision and Pattern Recognition | 2016

Identifying Metastases in Sentinel Lymph Nodes with Deep Convolutional Neural Networks.

Richard Y. Chen; Yating Jing; Hunter Jackson


Archive | 2012

The Masked Sample Covariance Estimator: An Analysis via the Matrix Laplace Transform

Richard Y. Chen; Alex Gittens; Joel A. Tropp


arXiv: Computer Vision and Pattern Recognition | 2018

Rethinking Monocular Depth Estimation with Adversarial Training.

Richard Y. Chen; Faisal Mahmood; Alan L. Yuille; Nicholas J. Durr


arXiv: Computer Vision and Pattern Recognition | 2018

Deep Adversarial Training for Multi-Organ Nuclei Segmentation in Histopathology Images

Faisal Mahmood; Daniel Borders; Richard Y. Chen; Gregory N. McKay; Kevan J. Salimian; Alexander Baras; Nicholas J. Durr

Collaboration


Dive into the Richard Y. Chen's collaboration.

Top Co-Authors

Avatar

Joel A. Tropp

California Institute of Technology

View shared research outputs
Top Co-Authors

Avatar

Roarke Horstmeyer

California Institute of Technology

View shared research outputs
Top Co-Authors

Avatar

Alex Gittens

California Institute of Technology

View shared research outputs
Top Co-Authors

Avatar

Benjamin Judkewitz

California Institute of Technology

View shared research outputs
Top Co-Authors

Avatar

Changhuei Yang

California Institute of Technology

View shared research outputs
Top Co-Authors

Avatar
Top Co-Authors

Avatar
Top Co-Authors

Avatar

Faisal Mahmood

Johns Hopkins University

View shared research outputs
Top Co-Authors

Avatar
Top Co-Authors

Avatar
Researchain Logo
Decentralizing Knowledge