Skip to yearly menu bar Skip to main content


Coresets via Bilevel Optimization for Continual Learning and Streaming

Zalan Borsos · Mojmir Mutny · Andreas Krause

Poster Session 3 #1082


Coresets are small data summaries that are sufficient for model training. They can be maintained online, enabling efficient handling of large data streams under resource constraints. However, existing constructions are limited to simple models such as k-means and logistic regression. In this work, we propose a novel coreset construction via cardinality-constrained bilevel optimization. We show how our framework can efficiently generate coresets for deep neural networks, and demonstrate its empirical benefits in continual learning and in streaming settings.

Chat is not available.