Scholar
Beau Coker
Google Scholar ID: Aob-E10AAAAJ
Postdoc, Columbia University
Citations & Impact
Citations
390
H-index
6
i10-index
4
Publications
17
Co-authors
0
Publications
Resume
Academic Achievements
- Talk at AISTATS about mean-field variational BNNs.
Research Experience
- Postdoc in the Center for Theoretical Neuroscience at Columbia University's Zuckerman Institute, working with John Cunningham on properties of variational inference.
Education
- PhD in Biostatistics from Harvard, advised by Finale Doshi-Velez and Brent Coull; MS in Statistics from Duke, advised by Cynthia Rudin.
Background
- Interested in probabilistic machine learning, particularly Bayesian neural networks (BNNs) and Gaussian processes (GPs). Thinking about questions like: How do we design priors that encode meaningful functional properties? What are the theoretical connections between BNNs and GPs, especially under approximate inference? Recently: How can we leverage implicit regularization in probabilistic modeling?