activity
20152018
most citedStochastic Cubic Regularization for Fast Nonconvex Optimization

46 citations · 80 across the 6 of their papers we have counts for

collaborators

6 papers

cs.DC20182 cited

Cataloging the Visible Universe through Bayesian Inference at Petascale

Jeffrey Regier, Kiran Pamnany, Keno Fischer +9

Astronomical catalogs derived from wide-field imaging surveys are an important tool for understanding the Universe. We construct an astronomical catalog from 55 TB of imaging data…

cs.LG201746 cited

Stochastic Cubic Regularization for Fast Nonconvex Optimization

Nilesh Tripuraneni, Mitchell Stern, Chi Jin +2

This paper proposes a stochastic variant of a classic algorithm---the cubic-regularized Newton method [Nesterov and Polyak 2006]. The proposed algorithm efficiently escapes saddle…

cs.LG20176 cited

A deep generative model for single-cell RNA sequencing with application to detecting differentially expressed genes

Romain Lopez, Jeffrey Regier, Michael Cole +2

We propose a probabilistic model for interpreting gene expression levels that are observed through single-cell RNA sequencing. In the model, each cell has a low-dimensional latent…

cs.LG20175 cited

A deep generative model for gene expression profiles from single-cell RNA sequencing

Romain Lopez, Jeffrey Regier, Michael Cole +2

We propose a probabilistic model for interpreting gene expression levels that are observed through single-cell RNA sequencing. In the model, each cell has a low-dimensional latent…

cs.LG20176 cited

Fast Black-box Variational Inference through Stochastic Trust-Region Optimization

Jeffrey Regier, Michael I. Jordan, Jon McAuliffe

We introduce TrustVI, a fast second-order algorithm for black-box variational inference based on trust-region optimization and the reparameterization trick. At each iteration, Trus…

astro-ph.IM201515 cited

Celeste: Variational inference for a generative model of astronomical images

Jeffrey Regier, Andrew Miller, Jon McAuliffe +5

We present a new, fully generative model of optical telescope image sets, along with a variational procedure for inference. Each pixel intensity is treated as a Poisson random vari…