Sun Dec 8th through Sat the 14th, 2019 at Vancouver Convention Center
This paper presents a method for online-within-online meta-learning where each task is revealed one after another and online learning is applied for within-task. The primal-dual online learning is the main ingredient. All of reviewers agree that the paper is well written and has valuable contributions, while a few relevant work is already available. During the discussion period, a reviewer with most negative review raised his/her score, enabling us to reach a consensus.