Geoff Pleiss
CIFAR AI Chair, Vector Institute
geoff.pleiss <at> stat.ubc.ca
I am an assistant professor in the Department of Statistics at the University of British Columbia, where I am an inaugural member of CAIDA's AIM-SI (AI Methods for Scientific Impact) cluster. I am also a Canada CIFAR AI Chair and a faculty member at the Vector Institute.
Previously, I was a postdoc at Columbia University with John P. Cunningham. I received my Ph.D. from the CS department at Cornell University in August 2020. where I was advised by Kilian Weinberger and also worked closely with Andrew Gordon Wilson.
My research interests intersect deep learning and probablistic modeling. Major focuses of my work include:
- neural networks,
- uncertainty quantification,
- probabilistic modeling, and
- Bayesian optimization.
More specifically, some recent interests include
- "reliable" neural networks,
- ensemble methods, and
- Gaussian processes.
I am also an active open source contributior. Most notably, I co-created and maintain the GPyTorch Gaussian process library with Jake Gardner.
Interested in joining my lab? I am looking for prospective M.S. students, Ph.D students, and postdocs with research interests similar to my own. While I am open to strong students with any ML/stats interests, I am particularly hoping to hire lab members for the following research topics:
- Bayesian optimization,
- spatiotemporal modeling, and
- neural network uncertainty quantification.
Recent and Selected Publications
For a full list of publications, please see my CV or my Google Scholar page.
-
NEWLayerwise proximal replay: A proximal point method for online continual learning.
- Jinsoo Yoo
- Yunpeng Liu
- Frank Wood
- Geoff Pleiss
— Under Submission -
NEWA Sober Look at LLMs for Material Discovery: Are They Actually Good for Bayesian Optimization Over Molecules?
- Agustinus Kristiadi
- Felix Strieth-Kalthoff
- Marta Skreta
- Pascal Poupart
- Alán Aspuru-Guzik
- Geoff Pleiss
— Under Submission -
NEWLarge-Scale Gaussian Processes via Alternating Projection
- Kaiwen Wu
- Jonathan Wenger
- Hadyn Jones
- Geoff Pleiss
- Jacob R. Gardner
— In AISTATS, 2024 -
NEWPathologies of Predictive Diversity in Deep Ensembles[featured paper]
- Taiga Abe
- E. Kelly Buchanan
- Geoff Pleiss
- John P. Cunningham
— In TMLR, 2024 -
CoLA: Exploiting Compositional Structure for Automatic and Efficient Numerical Linear Algebra
- Andres Potapczynski*
- Marc Anton Finzi*
- Geoff Pleiss
- Andrew Gordon Wilson
— In NeurIPS, 2023 -
Posterior and Computational Uncertainty in Gaussian Processes
- Jonathan Wenger
- Geoff Pleiss
- Marvin Pförtner
- Philipp Hennig
- John P. Cunningham
— In NeurIPS, 2022 -
Deep Ensembles Work, But Are They Necessary?
- Taiga Abe*
- E. Kelly Buchanan*
- Geoff Pleiss
- Richard Zemel
- John P. Cunningham
— In NeurIPS, 2022 -
The Limitations of Large Width in Neural Networks: A Deep Gaussian Process Perspective
- Geoff Pleiss
- John P. Cunningham
— In NeurIPS, 2021 -
GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration[spotlight]
- Jacob R. Gardner*
- Geoff Pleiss*
- David Bindel
- Kilian Q. Weinberger
- Andrew Gordon Wilson
— In NeurIPS, 2018 -
On Fairness and Calibration
- Geoff Pleiss*
- Manish Raghavan*
- Felix Wu
- Jon Kleinberg
- Kilian Q. Weinberger
— In NeurIPS, 2017 -
On Calibration of Modern Neural Networks
- Chuan Gao*
- Geoff Pleiss*
- Yu Sun*
- Kilian Q. Weinberger
— In ICML, 2017
Recent and Selected Talks
-
Dec. 2023Troubling Trajectories for Uncertainty Quantification and Decision Making with Neural Networks
A discussion of uncertainty quantification and my recent work on neural network ensembles. -
Spring 2022Bridging The Gap Between Deep Learning and Probabilistic Modeling
A talk connecting my Gaussian process and neural network research.
Selected Open Source
For a full list of respositories I actively contribute to, please see my Github page.
-
CoLA (Compositional Linear Algebra)Beta Release
A library for structured linear algebra operations in JaX and PyTorch.Coauthors: Andres Potapczynski, Marc Anton Finzi