Coresets via Bilevel Optimization for Continual Learning and Streaming

TL;DR

This paper introduces a bilevel optimization approach to create coresets for deep neural networks, enabling efficient continual learning and streaming data handling under resource constraints.

Contribution

It presents a novel bilevel optimization framework for constructing coresets applicable to deep neural networks, extending beyond simple models.

Findings

Effective coreset construction for deep neural networks.

Improved continual learning performance.

Enhanced streaming data handling efficiency.

Abstract

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.