Reproducibility Report: La-MAML: Look-ahead Meta Learning for Continual Learning

TL;DR

This paper evaluates La-MAML, a meta-learning algorithm designed for continual learning, claiming it outperforms existing methods in retention and interference metrics under limited compute conditions.

Contribution

The paper provides a reproducibility report verifying La-MAML's superior performance over state-of-the-art continual learning algorithms in key metrics.

Findings

La-MAML achieves higher Retained Accuracy (RA).

La-MAML shows reduced Backward Transfer-Interference (BTI).

The reproducibility confirms La-MAML's effectiveness.

Abstract

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.