Generative probabilistic programming: applications and new ideas

Опубликовано 22 июня 2016, 19:35

Probabilistic programming has recently attracted much attention in Computer Science and Machine Learning communities. I will briefly demonstrate two generative probabilistic graphics programs (models), which I contributed to develop. Then I will present ideas on two research directions I am interested in pursuing: a path to scaling up general-purpose approximate inference in probabilistic programs using parallelism, and a path to automatic programming via general-purpose approximate inference. This is based on joint work with Frank Wood, Vikash Mansinghka, Tejas Kulkarni, Daniel Selsam, Joshua Tenenbaum, et al.