Postdoc positions are available in the UBC Machine Learning Lab. These are targeted at scholars who have already published in top machine learning venues (like ICML or NIPS) or in similarly-ranked statistics or numerical optimization venues. If you are interested, please contact me for details (and include a CV) before the end of May.
Research
List of Publications - with links to
code, presentations/posters, and appendices.
Selected recent papers:
NIPS 2015 (Stop Wasting My Gradients: Practical SVRG)
ICML 2015 (Coordinate descent converges faster with the Gauss-Southwell rule than random selection)
AI/Stats 2015 (Non-Uniform Stochastic Average Gradient for Training Conditional Random Fields)
arXiv 2013 (Minimizing Finite Sums with the Stochastic Average Gradient)
ICML 2013 (Block-coordinate Frank-Wolfe Optimization for Structural SVMs)
NIPS 2012 (A Stochastic Gradient Method with an Exponential Convergence Rate for Finite Training Sets)
SISC 2012 (Hybrid Deterministic-Stochastic Methods for Data Fitting)
NIPS 2011 (Convergence Rates of Inexact Proximal-Gradient Methods for Convex Optimization)
Opt in ML 2011 (Projected Newton-type Methods in Machine Learning)
Phd Thesis 2010 (Graphical Model Structure Learning with L1-Regularization)