Automated, Scalable Bayesian Inference via Coresets

Boston Bayesians
Boston Bayesians
Public group
Location image of event venue


Our June meeting will feature a talk from Trevor Campbell, assistant professor of statistics at the University of British Columbia. Trevor will talk about Scalable Bayesian Inference via Coresets. Join us to learn about this interesting topic, and share your story with fellow Bayesians.

Automated, Scalable Bayesian Inference via Coresets

The automation of posterior inference in Bayesian data analysis has enabled experts and nonexperts alike to use more sophisticated models, engage in faster exploratory modeling and analysis, and ensure experimental reproducibility. However, standard automated posterior inference algorithms are not tractable at the scale of massive modern datasets, and modifications to make them so are typically model-specific, require expert tuning, and can break theoretical guarantees on inferential quality. This talk will instead take advantage of data redundancy to shrink the dataset itself as a preprocessing step, forming a "Bayesian coreset." The coreset can be used in a standard inference algorithm at significantly reduced cost while maintaining theoretical guarantees on posterior approximation quality. The talk will include an intuitive formulation of Bayesian coreset construction as sparse vector sum approximation, an automated coreset construction algorithm that takes advantage of this formulation, strong theoretical guarantees on posterior approximation quality, and applications to a variety of real and simulated datasets.

Speaker Bio:
Trevor Campbell is an assistant professor of statistics at the University of British Columbia (starting July 2018). His research focuses on automated, scalable Bayesian inference algorithms, Bayesian nonparametrics, streaming data, and Bayesian theory. Trevor was previously a postdoctoral associate advised by Tamara Broderick in the Computer Science and Artificial Intelligence Laboratory (CSAIL) and Institute for Data, Systems, and Society (IDSS) at MIT, a Ph.D. candidate under Jonathan How in the Laboratory for Information and Decision Systems (LIDS) at MIT, and before that was in the Engineering Science program at the University of Toronto. Publications and projects are available online at

* 6:30pm: Meet and Greet. Networking
* 7:00pm: Talk by Trevor Campbell + Q&A
* 8:00pm: Networking
* 8:45pm: End of event


This event is sponsored by QuantumBlack, a McKinsey Company