Peter BARTLETT
(University of California at Berkeley, Berkeley AI Research Lab)
Deep learning: a statistical perspective.
Deep learning, the technology underlying the recent progress in AI, has revealed some major surprises from the perspective of theory. These methods seem to achieve their outstanding performance through different mechanisms from those studied in classical learning theory, mathematical statistics, and optimization theory. Simple gradient methods find excellent solutions to non-convex optimization problems, and without any explicit effort to control model complexity, they exhibit excellent prediction performance in practice. This lecture series will review recent progress on deep learning, viewed as a nonparametric statistical methodology, as well as some of the intriguing questions that it raises.
