Reviews: Gradient based sample selection for online continual learning

This paper proposes an approach to optimally select samples for a small replay buffer to perform continual learning (CL) without forgetting. GEM/A-GEM) the problem is formulated from the perspective of constrained optimisation (minimise loss on current sample subject to loss not increasing on previous ones). Unlike GEM, with clear separation and knowledge of tasks, this approach addresses the general non-stationary learning problem. The paper proposes a theoretical argument for using the variance of gradients to select samples for the buffer. One related work that could also be cited is "Adapting Auxiliary Losses using Gradient Similarity", by Du et al, 2018 (https://arxiv.org/abs/1812.02224)