A0604
Title: The Bayesian learning rule
Authors: Mohammad Emtiyaz Khan - RIKEN Center for AI project (Japan) [presenting]
Abstract: It will be shown that a wide variety of machine-learning algorithms are instances of a single learning rule called the Bayesian learning rule. The key idea in deriving such algorithms is to approximate the posterior using candidate distributions estimated by using natural gradients. Different candidate distributions result in different algorithms and further approximations to natural gradients give rise to variants of those algorithms.
