Dr. Mark Schmidt

Mark Schmidt has been an assistant professor in the Department of Computer Science at the University of British Columbia since 2014, and is a Canada Research Chair and Alfred P. Sloan Fellow. From 2011 through 2013 he worked at the École normale supérieure in Paris on inexact and stochastic convex optimization methods. He finished his M.Sc. in 2005 at the University of Alberta working as part of the Brain Tumor Analysis Project, and his Ph.D. in 2010 at the University of British Columbia working on graphical model structure learning with L1-regularization.

Current Research Focus

Dr. Schmidt’s research focuses on developing faster algorithms for large-scale machine learning, with an emphasis on methods with provable convergence rates and that can be applied to structured prediction problems. These have many applications, including computer vision, medical image analysis, and natural language understanding. He has worked at Siemens Medical Solutions on heart motion abnormality detection, with Michael Friedlander in the Scientific Computing Laboratory at the University of British Columbia on semistochastic optimization methods, and with Anoop Sarkar at Simon Fraser University on large-scale training of natural language models.

Example Project

“Tractable Big Data and Big Models in Machine Learning”

In nearly all fields of science and engineering, the amount of data we collect is growing at unprecedented rates. Machine learning is one of the key tools we use to make sense of these ever-growing quantities of data ('big data'), and it is now being used to solve very complicated tasks by fitting increasingly-complicated models to these huge data sets ('big models'). The successes and potential of large-scale machine learning are driving the need to develop techniques that can consider constantly-increasing data and model sizes, and the objective of this proposal is to advance the state of the art in fitting big models to big data sets. Building on my existing work showing that special model structures can be used to give order-of-magnitude improvements in runtimes, the outcome of this research will be new techniques that are substantially faster than existing techniques (e.g., polynomial-time instead of exponential-time, or improving runtime by a factor that may be as large as the data or model size).

Research Keywords

Machine Learning, Numerical Optimization, Probabilistic Graphical Models, Causality