Home

In Brief: I am just starting as an Assistant Professor in the Department of Mathematics and Statistics at the University of Massachusetts Amherst. 

Methodologically, I am interested in the nexus of statistics and optimization, especially dimensionality reduction, surrogate modeling and variational Bayes. Recently, I have been particularly interested in approximating discontinuous functions with smooth ones, and vice versa. 

Like many statisticians, I am grateful for the opportunity to work on diverse applications. But my focus is on human migration and refugee-like situations as well as quantitative social science more broadly. 

I'm very thankful to AAAS for the opportunity to give a webinar (with Geraldine Henningsen of UNHCR and Ali Arab of Georgetown) on the modeling of forced displacement, a recording of which is available on Youtube.

Software:

- R package activegp: Design for and implementation of black-box sensitivity analysis using Gaussian Processes and the Active Subspace Method.

To get started, just do:

R> install.packages("activegp")

R>example(activegp)

Selected Research Documents:

(For a full list, see my Google Scholar)

- Nathan Wycoff (2024+) Regression Trees Know Calculus, Under Review, <arXiv>.

- Nathan Wycoff (2024) Surrogate Active Subspaces for Jump-Discontinuous Functions, AISTATS '24 <PMLR> <arXiv> <GitHub>.

- Nathan Wycoff, Lisa O. Singh, Ali Arab, Katharine M. Donato, Helge Marahrens (2024) The digital trail of Ukraine’s 2022 refugee exodus, Journal of Computational Social Science, <JCSO> <GitHub>.

- Nathan Wycoff, Mickaël Binois & Stefan M. Wild (2021) Sequential Learning of Active Subspaces, Journal of Computational and Graphical Statistics,  <arXiv>, <JCGS>. 

Previous Work Experience:

Teaching Experience (at Virginia Tech):

Education: