Skip to yearly menu bar Skip to main content


Poster
in
Workshop: Distribution shifts: connecting methods and applications (DistShift)

Gradient-matching coresets for continual learning

Lukas Balles · Giovanni Zappella · Cedric Archambeau


Abstract:

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.

Chat is not available.