Geoff Pleiss
About
Appointed Canada CIFAR AI Chair – 2024
Pleiss’s research interests encompass a wide range of topics in machine learning, including deep learning, uncertainty quantification, probabilistic modeling, and Bayesian optimization. His work targets the intersection of predictive machine learning and scientific discovery, with the goal of improving the accessibility and reliability of AI-guided inferences. He is also an avid open source contributor, having co-founded the GPyTorch, LinearOperator, and CoLA software libraries.
Relevant Publications
- Abe, T., Buchanan, E. K., Pleiss, G., Zemel, R., & Cunningham, J. P. (2022). Deep ensembles work, but are they necessary?. In Advances in Neural Information Processing Systems.
- Pleiss, G., Zhang, T., Elenberg, E., & Weinberger, K. Q. (2020). Identifying mislabeled data using the area under the margin ranking. In Advances in Neural Information Processing Systems.
- Gardner, J., Pleiss, G., Weinberger, K. Q., Bindel, D., & Wilson, A. G. (2018). GPyTorch: Blackbox matrix-matrix Gaussian process inference with GPU acceleration. In Advances in neural information processing systems.
- Pleiss, G., Raghavan, M., Wu, F., Kleinberg, J., & Weinberger, K. Q. (2017). On fairness and calibration. In Advances in neural information processing systems.
- Guo, C., Pleiss, G., Sun, Y., & Weinberger, K. Q. (2017). On calibration of modern neural networks. In International conference on machine learning.