Continual Learning with Distributed Optimization: Does CoCoA Forget?
This addresses continual learning in distributed settings, which is incremental as it applies an existing algorithm to a new problem context.
The paper investigates whether the distributed optimization algorithm COCOA can perform continual learning across sequential tasks without forgetting previous ones. Their analysis shows COCOA can achieve this under certain problem dimensions and data assumptions, with convergence and error performance depending on over/under-parameterization.
We focus on the continual learning problem where the tasks arrive sequentially and the aim is to perform well on the newly arrived task without performance degradation on the previously seen tasks. In contrast to the continual learning literature focusing on the centralized setting, we investigate the distributed estimation framework. We consider the well-established distributed learning algorithm COCOA. We derive closed form expressions for the iterations for the overparametrized case. We illustrate the convergence and the error performance of the algorithm based on the over/under-parameterization of the problem. Our results show that depending on the problem dimensions and data generation assumptions, COCOA can perform continual learning over a sequence of tasks, i.e., it can learn a new task without forgetting previously learned tasks, with access only to one task at a time.