Gradient-matching coresets for continual learning
This addresses the challenge of efficient memory usage in continual learning for AI systems, but it is incremental as it builds on existing coreset and rehearsal techniques.
The paper tackled the problem of selecting a coreset for rehearsal memory in continual learning by proposing a gradient-matching method, and it achieved performance competitive with strong baselines like reservoir sampling across various memory sizes.
We devise a coreset selection method based on the idea of gradient matching: The gradients induced by the coreset should match, as closely as possible, those induced by the original training dataset. We evaluate the method in the context of continual learning, where it can be used to curate a rehearsal memory. Our method performs strong competitors such as reservoir sampling across a range of memory sizes.