Andrew Frank - Home

Notice: I defended my thesis in summer 2013 and now work at Apple in Seattle.


I am a graduate student in the Computer Science Department at the University of California, Irvine. I am fortunate to be co-advised by Alex Ihler and Padhraic Smyth, and as such I enjoy "dual citizenship" in the Statistical Learning and Inference and DataLab groups at UCI. I plan to defend in the summer of 2013.

My research is in the area of approximate inference for probabilistic graphical models. On the theoretical side, I am interested combining sampling-based approximations with variational message-passing algorithms. On the applied side, I am interested in using graphical models to manage association uncertainty in multi-target tracking. Check out my research page for short blurbs about my major projects, along with publications and code.


Thesis: Frank, A. Variational Message-Passing: Extension to Continuous Variables and Applications in Multi-Target Tracking. PhD Thesis. University of California, Irvine, 2013. (pdf) (bib)
Publication: Frank, A.; Smyth, P.; Ihler, A.; , "A graphical model representation of the track-oriented multiple hypothesis tracker," Statistical Signal Processing Workshop (SSP), 2012 IEEE , vol., no., pp.768-771, 5-8 Aug. 2012. (pdf) (bib) (poster)
Talk: New applications of graphical models for multitarget tracking. Presented at the UCI AI/ML seminar series. (slides)
I am co-organizing a new Machine Learning Reading Group with Andrew Gelfand and Chris Dubois. Join us on Wednesdays from 12-1 to discuss the week's paper and bring suggestions for what to read next. You can subscribe to the mailing list to receive weekly notifications with links to the paper.
Internship: LinkedIn Product Analytics team with mentor Monica Rogati.
Publication: van Leeuwen, T. T., A. J. Frank, Y. Jin, P. Smyth, M. L. Goulden, G. R. van der Werf, and J. T. Randerson (2011), Optimal use of land surface temperature data to detect changes in tropical forest cover, J. Geophys. Res., 116, G02002, <doi:10.1029/2010JG001488>. (pdf) (bib)
I am now the curator for the UCI Machine Learning Repository.
Talk: Belief Propagation in a Continuous World. Presented at the UCI AI/ML seminar series. (slides)
Publication: A. Ihler, A. Frank, and P. Smyth. Particle-based variational inference for continuous systems. Neural Information Processing Systems, 2009. (pdf) (bib) (poster)
Third place: UCSD Data Mining Contest, supervised learning category. Fellow team members: Todd Johnson, David Orendorff, Julien Neel.