Reproducibility Report: La-MAML: Look-ahead Meta Learning for Continual Learning
This is an incremental reproducibility study for researchers in continual learning, focusing on validating performance claims.
The paper verifies the reproducibility of La-MAML, a meta-learning algorithm for continual learning that claims to outperform state-of-the-art methods in retained accuracy and backward transfer-interference metrics.
The Continual Learning (CL) problem involves performing well on a sequence of tasks under limited compute. Current algorithms in the domain are either slow, offline or sensitive to hyper-parameters. La-MAML, an optimization-based meta-learning algorithm claims to be better than other replay-based, prior-based and meta-learning based approaches. According to the MER paper [1], metrics to measure performance in the continual learning arena are Retained Accuracy (RA) and Backward Transfer-Interference (BTI). La-MAML claims to perform better in these values when compared to the SOTA in the domain. This is the main claim of the paper, which we shall be verifying in this report.