2020/06/06 by Zalán Borsos, Borsos, Zalán, Mojmír Mutný +3 · 19 citations
Computer Science · Engineering · #Domain Adaptation and Few-Shot Learning #Sparse and Compressive Sensing Techniques #Machine Learning and Algorithms
paper · pdf · doi:10.48550/arxiv.2006.03875
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.