Timezone: »

 
Poster
The Ideal Continual Learner: An Agent That Never Forgets
Liangzu Peng · Paris Giampouras · Rene Vidal

Wed Jul 26 05:00 PM -- 06:30 PM (PDT) @ Exhibit Hall 1 #324
in Poster Session 4 »

The goal of continual learning is to find a model that solves multiple learning tasks which are presented sequentially to the learner. A key challenge in this setting is that the learner may "forget" how to solve a previous task when learning a new task, a phenomenon known as catastrophic forgetting. To address this challenge, many practical methods have been proposed, including memory-based, regularization-based and expansion-based methods. However, a rigorous theoretical understanding of these methods remains elusive. This paper aims to bridge this gap between theory and practice by proposing a new continual learning framework called "Ideal Continual Learner" (ICL), which is guaranteed to avoid catastrophic forgetting by construction. We show that ICL unifies multiple well-established continual learning methods and gives new theoretical insights into the strengths and weaknesses of these methods. We also derive generalization bounds for ICL which allow us to theoretically quantify "how rehearsal affects generalization". Finally, we connect ICL to several classic subjects and research topics of modern interest, which allows us to make historical remarks and inspire future directions.

[ PDF] 

Author Information

Liangzu Peng (University of Pennsylvania)
Paris Giampouras (Mathematical Institute for Data Science, Johns Hopkins University)
Rene Vidal (University of Pennsylvania)

More from the Same Authors