Jie Ren
I am a research scientist in Google Brain. My recent research interest is robust and reliable deep learning, with a focus on uncertainty quantification and out-of-distribution detection. I received my PhD in Computational Biology and Bioinformatics and a MSc in Statistics from the University of Southern California, 2017. I was a post-doctoral fellow at USC from 2017-2018, and after that I joined Google Brain as an AI resident for one year. Please see my webpage for more information https://jessieren.github.io/.
Authored Publications
Sort By
Google
Building One-class Detector for Anything: Open-vocabulary Zero-shot OOD Detection Using Text-image Models
Yunhao Ge
Jiaping Zhao
Laurent Itti
Knowledge and Logical Reasoning workshop @ ICML (2023)
Morse Neural Networks for Uncertainty Quantification
Clara Huiyi Hu
ICML 2023 Workshop on Structured Probabilistic Inference & Generative Modeling (2023)
Plex: Towards Reliability using Pretrained Large Model Extensions
Du Phan
Mark Patrick Collier
Zi Wang
Zelda Mariet
Clara Huiyi Hu
Neil Band
Tim G. J. Rudner
Karan Singhal
Joost van Amersfoort
Andreas Christian Kirsch
Rodolphe Jenatton
Honglin Yuan
Kelly Buchanan
D. Sculley
Yarin Gal
ICML 2022 Pre-training Workshop (2022)
A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness
Shreyas Padhy
Zi Lin
Yeming Wen
Ghassen Jerfel
Journal of Machine Learning Research (2022)
Does Your Dermatology Classifier Know What It Doesn't Know? Detecting the Long-Tail of Unseen Conditions
Aaron Loh
Basil Mustafa
Nick Pawlowski
Jan Freyberg
Zach William Beaver
Nam Vo
Peggy Bui
Samantha Winter
Patricia MacWilliams
Umesh Telang
Taylan Cemgil
Jim Winkens
Medical Imaging Analysis (2021)
Likelihood Ratios for Out-of-Distribution Detection
Peter J. Liu
Mark DePristo
Josh Dillon
arXiv preprint arXiv:1906.02845 (2019)
Can You Trust Your Model’s Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift
Yaniv Ovadia
D. Sculley
Sebastian Nowozin
Josh Dillon
Advances in Neural Information Processing Systems (2019)
