Review for NeurIPS paper: Online Multitask Learning with Long-Term Memory

Weaknesses: Unfortunately, the paper has several major weaknesses: * In the online multitask expert setting (Section 3), the authors claim that their framework is more general than the related work [1,3,4,7], by allowing switches between hypotheses for each class. Yet, the number m of modes is known in advance. So, for each task i \in [s], we know that there are at most m best hypotheses. Thus, unless I missed something, we can simply replace the s tasks by m \times s ones (i.e. each task in [s] consists of m different subtasks), and just apply the results obtained by [1] for the shifting multitask problem with expert advice (Corollary 1 in [1]) in order to get a bound that is essentially similar to (3). Still, I am aware that there are some differences between [1] and the present paper.