Gradient-matching coresets for continual learning

12/09/2021
by   Lukas Balles, et al.
0

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.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset