Learning Theory for Continual and Meta-Learning

by · Jul 12, 2020 · 479 views ·

ICML 2020

In recent years we have seen an explosion of approaches that aim at transferring information between different learning tasks, in particular meta-learning and continual or lifelong learning. In my talk, I discuss ways to study these formally, using tools from learning theory that abstract away the specific details of implementation. In particular, I will discuss which assumptions one has to make on the tasks to be learned in order to guarantee a successful transfer of information.