Timezone: »
Gradient-matching coresets for continual learning
Lukas Balles · Giovanni Zappella · Cedric Archambeau
Event URL: https://openreview.net/forum?id=_9BuV5WjiUv »
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.
Author Information
Lukas Balles (Amazon Web Services)
Giovanni Zappella (Amazon, Berlin)
Cedric Archambeau (Amazon)
More from the Same Authors
-
2020 : Bayesian optimization by density ratio estimation »
Louis Tiao · Aaron Klein · Cedric Archambeau · Edwin Bonilla · Matthias W Seeger · Fabio Ramos -
2019 Poster: Learning search spaces for Bayesian optimization: Another view of hyperparameter transfer learning »
Valerio Perrone · Huibin Shen · Matthias Seeger · Cedric Archambeau · Rodolphe Jenatton -
2018 Poster: Scalable Hyperparameter Transfer Learning »
Valerio Perrone · Rodolphe Jenatton · Matthias W Seeger · Cedric Archambeau -
2013 Poster: A Gang of Bandits »
Nicolò Cesa-Bianchi · Claudio Gentile · Giovanni Zappella -
2012 Poster: A Linear Time Active Learning Algorithm for Link Classification »
Nicolò Cesa-Bianchi · Claudio Gentile · Fabio Vitale · Giovanni Zappella -
2011 Poster: See the Tree Through the Lines: The Shazoo Algorithm »
Fabio Vitale · Nicolò Cesa-Bianchi · Claudio Gentile · Giovanni Zappella -
2011 Spotlight: See the Tree Through the Lines: The Shazoo Algorithm »
Fabio Vitale · Nicolò Cesa-Bianchi · Claudio Gentile · Giovanni Zappella