- Conference Paper
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. Mehr anzeigen
BuchtitelAdvances in Neural Information Processing Systems 33
Seiten / Artikelnummer
Organisationseinheit03908 - Krause, Andreas / Krause, Andreas
167212 - Scaling Up by Scaling Down: Big ML via Small Coresets (SNF)
815943 - Reliable Data-Driven Decision Making in Cyber-Physical Systems (EC)
AnmerkungenDue to the Coronavirus (COVID-19) the conference was conducted virtually.