About
I'm a Technical Staff member at MIT Lincoln Laboratory working on applications of machine learning to cybersecurity. I completed a PhD in machine learning at MIT advised by Tamara Broderick; my PhD research mostly focused on issues of approximate computation and robustness. Prior to graduate school, I was at Brown University for my undergraduate and worked for a year at Vision Systems, Inc. in Providence, RI.
Refereed Publications
- Measuring the robustness of Gaussian processes to kernel choice.
W. T. Stephenson, S. Ghosh, T. D. Nguyen, M. Yurochkin, S. K. Deshpande, and T. Broderick. AISTATS. 2022.
Paper
- Can we globally optimize cross-validation loss? Quasiconvexity in ridge regression.
W. T. Stephenson, Z. Frangella, M. Udell, and T. Broderick. NeurIPS. 2021.
Paper
- Approximate cross-validation with low-rank data in high dimensions.
W. T. Stephenson, M. Udell, and T. Broderick. NeurIPS. 2020.
Paper
- Approximate cross-validation for structured models.
S. Ghosh*, W. T. Stephenson*, T. D. Nguyen, S. K. Deshpande, and T. Broderick (* denotes equal contribution) NeurIPS. 2020.
Paper
- Approximate cross-validation in high dimensions with guarantees.
W. T. Stephenson and T. Broderick. AISTATS. 2020.
Paper
- A Swiss army infinitesimal jackknife.
R. Giordano, W. T. Stephenson, R. Liu, M. I. Jordan, and T. Broderick. AISTATS. 2019.
(Notable paper award) Paper
- Sensitivity of Bayesian inference to data perturbations.
L. Masoero*, W. T. Stephenson* and T. Broderick. (* denotes equal contribution) Symposium on Advances in Approximate Bayesian Inference. 2018.
Paper
- Understanding covariance estimates in expectation propagation.
W. T. Stephenson and T. Broderick. NIPS 2016 Workshop on Advances in Approximate Bayesian Inference. 2016.
Paper
- Scalable adaptation of state complexity for nonparametric hidden Markov models.
M. Hughes, W. T. Stephenson, and E. Sudderth. NIPS. 2015.
Paper