I enjoy working on problems in statistical machine learning and applied statistics, especially developing methods that might be of direct use to scientists (or others with large datasets). A particular interest of mine is in using convex optimization to tackle the challenges of high-dimensional datasets.
William Nicholson, Jacob Bien, David Matteson (2014) Hierarchical Vector Autoregression. [pdf]
Jacob Bien and Marten Wegkamp (2013) Discussion of “Correlated variables in regression: clustering and sparse estimation” by Bühlmann et al. Journal of Statistical Planning and Inference. 143(11), 1859-1862. [pdf]
Robert Tibshirani, Jacob Bien, Jerome Friedman, Trevor Hastie, Noah Simon, Jonathan Taylor, and Ryan Tibshirani (2012) Strong Rules for Discarding Predictors in Lasso-type Problems. Journal of the Royal Statistical Society, Series B. 74(2). 245-266 [pdf]
Jacob Bien, Ya Xu, and Michael Mahoney (2010) CUR from a Sparse Optimization Viewpoint. Advances in Neural Information Processing Systems 23. [pdf]
Neema Moraveji, Daniel Russell, Jacob Bien, David Mease (2011) Measuring Improvement in User Search Performance Resulting from Optimal Search Tips. Proceedings of SIGIR 2011. [abstract]
BTRY/STSCI 4090: Theory of Statistics (Spring 2015)
BTRY 6010: Statistical Methods I (Fall 2014)
BTRY/STSCI 4090: Theory of Statistics (Spring 2014)
BTRY 4950/7950: Statistical Consulting (Spring 2014)
BTRY 7180: Generalized Linear Models (Fall 2013)
BTRY/STSCI 4090: Theory of Statistics (Spring 2013)
For CVX users: Here is an R package I wrote to call CVX from R.
I enjoy juggling. Here are some videos of me club passing with the Stanford Court Jugglers. I am to the far left in this video and this video and am in the front right in this video (if you look closely, you'll notice that every pass I throw is to the person behind me).
Here's my solution to an incredible physics puzzle involving elastic collisions and the digits of pi. I wrote this up in the summer of 2010, after hearing the problem from Caitlin Stanton and Tucker Hiatt. Section 1 states the problem. My favorite part is Section 6, which gives a simple explanation for the link between having constant kinetic energy and pi.
Department of Biological Statistics and Computational Biology
1178 Comstock Hall
Ithaca, NY 14853