论文标题
通过二线优化的核心进行持续学习和流式传输
Coresets via Bilevel Optimization for Continual Learning and Streaming
论文作者
论文摘要
核心是小型数据摘要，足以用于模型培训。它们可以在线维护，从而在资源限制下有效地处理大型数据流。但是，现有的结构仅限于简单的模型，例如K-均值和逻辑回归。在这项工作中，我们提出了一种新型的核心结构，该核能结构是通过基数受限的二元优化。我们展示了我们的框架如何有效地生成深层神经网络的核心，并在不断学习和流媒体环境中展示其经验益处。
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.
