Invited Talk
in
Workshop: Subset Selection in Machine Learning: From Theory to Applications

Data Summarization via Bilevel Coresets

Andreas Krause

2021 Invited Talk
in
Workshop: Subset Selection in Machine Learning: From Theory to Applications

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 and streaming deep learning, as well as active semi-supervised learning.

Joint work with Zalán Borsos, Mojmír Mutny and Marco Tagliasacchi

Speaker

Andreas Krause

Andreas Krause is a Professor of Computer Science at ETH Zurich, where he leads the Learning & Adaptive Systems Group, serves as Academic Co-Director of the Swiss Data Science Center, Chair of the ETH AI Center, and co-founded the ETH spin-off LatticeFlow AI. He is a Fellow at the Max Planck Institute for Intelligent Systems, ACM Fellow, IEEE Fellow, ELLIS Fellow and a Microsoft Research Faculty Fellow. He received the Rössler Prize, ERC Starting Investigator and Consolidator grants, the German Pattern Recognition Award, an NSF CAREER award, Test of Time awards at KDD 2019 and ICML 2020, as well as the ETH Golden Owl teaching award. Andreas Krause served as Program Co-Chair for ICML 2018 and General Chair for ICML 2023 and serves as Action Editor for the Journal of Machine Learning Research. From 2023-24, he served on the United Nations’ High-level Advisory Body on AI.

Video

Chat is not available.