My current research focuses on applying machine learning techniques to model global-scale patterns of biodiversity and species distributions. I am also interested in birth-death processes for population dynamics, niche modeling with animal movement data, and point-process models for metacommunity analysis. In general, I’m interested in developing models that unify multiple traditional ecological processes. Before coming to Yale, I completed my PhD in computer science at the University of Massachusetts, Amherst, where my research focused on novel demography models for populations of unmarked individuals.
Learning in integer latent variable models with nested automatic differentiation by Daniel Sheldon, Kevin Winner, and Debora Sujono. In Proceedings of the 35th International Conference on Machine Learning, ICML 2018, pages 4622–4630, 2018.
Statistical inference for home range overlap by Kevin Winner, Michael J. Noonan, Chris H. Fleming, Kirk Olson, Thomas Mueller, Dan Sheldon, and Justin M. Calabrese. In Methods in Ecology and Evolution, 2018.
Exact inference for integer latent-variable models by Kevin Winner, Debora Sujono, and Daniel Sheldon. In Proceedings of the 34th International Conference on Machine Learning - Volume 39, 2017.
Probabilistic inference with generating functions for Poisson latent variable models by Kevin Winner and Daniel Sheldon. In Advances in Neural Information Processing Systems 30, 2016.