The van Eeden seminar is presented each year by the University of British Columbia’s Department of Statistics. The invited speaker is a prominent statistician chosen by the department’s graduate students. This year’s vitual seminar is sponsored by CANSSI and features Dr. Kevin Patrick Murphy, a research scientist at Google.
For more information and to register for the seminar, visit the event page on the UBC statistics department website.
WATCH THE VIDEO RECORDING OF THIS SEMINAR ON YOUTUBE
“I will present a unified perspective on the field of machine learning research, following the structure of my recent book, Probabilistic Machine Learning: Advanced Topics (https://probml.github.io/book2). In particular, I will discuss various models and algorithms for tackling the following four key tasks, which I call the “pillars of ML”: prediction, control, discovery and generation. For each of these tasks, I will also briefly summarize a few of my own contributions, including methods for robust prediction under distribution shift, statistically efficient online decision making, discovering hidden regimes in high-dimensional time series data, and for generating high-resolution images.”