Education
-
2018 - 2023
PhD in Biostatistics
Harvard University | Cambridge, MA
- Thesis: Misspecification, Nonstationarity, and Approximate Inference in Gaussian Processes and Bayesian Neural Networks
-
2016 - 2018
MS in Statistical Science
Duke University | Durham, NC
-
2009 - 2013
BS in Engineering Science
Tufts University | Medford, MA
Research Experience
-
2023 -
Postdoc | Zuckerman Institute, Columbia University
- Advisor: John Cunningham
- Topics: Implicit regularization in deep learning, variational inference
-
2019 - 2023
Graduate Research Assistant | Harvard School of Engineering and Applied Sciences
- Advisor: Finale Doshi-Velez
- Topics: Bayesian neural networks, GPs, variational inference
-
2019 - 2023
Environmental Health
Graduate Research Assistant | Harvard T.H. Chan School of Public Health
- Advisor: Brent Coull
- Topics: variable selection, approximate GPs
-
2017 - 2018
Graduate Research Assistant | Duke University Department of Computer Science
- Advisor: Cynthia Rudin
- Topics: robust statistics, recidivism prediction, nonlinear dynamical systems
-
2012 - 2013
Undergraduate Research Assistant | Tufts University Department of Physics
- Advisor: Tim Atherton
- Topics: Ising systems, critical phenomena in financial markets
Publications
- Variational Deep Learning via Implicit Regularization. Jonathan Wenger*, Beau Coker*, Juraj Marusic, John P. Cunningham. Pending review, 2025.
- Implications of Gaussian process kernel mismatch for out-of-distribution data. Beau Coker, Finale Doshi-Velez. In ICML workshops Spurious correlations, Invariance, and Stability (SCIS) and Structured Probabilistic Inference and Generative Modeling (SPIGM), 2023.
- An Empirical Analysis of the Advantages of Finite v.s. Infinite Width Bayesian Neural Networks. Jiayu Yao, Yaniv Yacoby, Beau Coker, Weiwei Pan, Finale Doshi-Velez. In NeurIPS workshop on Gaussian Processes, Spatiotemporal Modeling, and Decision-making Systems, 2022.
- Towards a Unified Framework for Uncertainty-aware Nonlinear Variable Importance Estimation with Theoretical Guarantees. Wenying Deng, Beau Coker, Rajarshi Mukherjee, Jeremiah Zhe Liu, and Brent A. Coull. In Advances in Neural Information Processing Systems (NeurIPS), 2022.
- Wide Mean-Field Variational Bayesian Neural Networks Ignore the Data. Beau Coker*, David Burt*, Wessel Bruinsma*, Weiwei Pan, Finale Doshi-Velez. In Proceedings of The 25th International Conference on Artificial Intelligence and Statistics (AISTATS), 2022.
- Wide Mean-Field Variational Bayesian Neural Networks Ignore the Data. Beau Coker, Weiwei Pan, Finale Doshi-Velez. In ICML Wwrkshop on Uncertainty & Robustness in Deep Learning (UDL), 2021.
- Selected for a contributed talk.
- A Theory of Statistical Inference for Ensuring the Robustness of Scientific Results. Beau Coker, Cynthia Rudin, Gary King. Management Science, 67, 2021.
- PoRB-Nets Poisson Process Radial Basis Function Networks. Beau Coker, Melanie F. Pradier, Finale Doshi-Velez. In Proceedings of the 36th Conference on Uncertainty in Artificial Intelligence (UAI), 2020.
- The Age of Secrecy and Unfairness in Recidivism Prediction. Cynthia Rudin, Caroline Wang, Beau Coker. Harvard Data Science Review (HDSR), 2020.
- Learning a Latent Space of Highly Multidimensional Cancer Data. Ben Kompa, Beau Coker. In Pacific Symposium on Biocomputing, 25, 2020.
- *Equal contribution
Teaching Experience
-
2019 - 2023
Teaching Fellow
Harvard University | Cambridge, MA
- Data Science II | Biostatistics 261 (Spring 2021, 2022, 2023)
- Reproducible Data Science | Biostatistics 270 (Winter 2022, 2023)
- Applied Bayesian Analysis | Biostatistics 270 (Fall 2020, 2021)
- Applied Regression Analysis | Biostatistics 210 (Fall 2019, Spring 2020)
-
2017 - 2018
Teaching Assistant
Duke University | Durham, NC
- Probabilistic Machine Learning | Statistical Science 561 (Spring 2018)
- Data Analysis and Statistical Inference | Statistical Science 101 (Spring 2017)
Presentations
-
2024
- Invited talk at JSM session on Advances in Inference and Theory for Bayesian Neural Networks | Portland, OR
- NSF AI Institute for Artificial and Natural Intelligence Visit Day | Columbia University
-
-
-
2020
- HughesLab group meeting | Virtual (PI Mike Hughes, Tufts University)
-
2019
- 12th International Conference on Bayesian Nonparametrics | Oxford, UK (poster)
-
2018
- Triangle Machine Learning Day | Durham, NC (poster)
Industry Experience
-
2014 - 2016
State Street Associates
Assistant Vice President | Cambridge, MA
- Lead analyst on the Liquid Private Equity Index, which tracks private equity with publicly traded securities.
- Researched how market turbulence, systemic risk, illiquidity, and currency movements impact portfolio management
-
2013 - 2014
State Street Global Markets
Senior Associate | Boston, MA
- Completed three 4-month rotations through onboarding processes flows, currency hedging, and macro strategy (currency trading)
-
2012
State Street Associates
Intern | Cambridge, MA
- Worked on portfolio optimization by minimizing transaction costs