Data Summarization via Bilevel Optimization


Loading...

Date

2024

Publication Type

Journal Article

ETH Bibliography

yes

Citations

Altmetric

Data

Abstract

The increasing availability of massive data sets poses various challenges for machine learning. Prominent among these is learning models under hardware or human resource straints. In such resource -constrained settings, a simple yet powerful approach is operating on small subsets of the data. Coresets are weighted subsets of the data that provide approximation guarantees for the optimization objective. However, existing coreset constructions are highly model -specific and are limited to simple models such as linear regression, logistic regression, and k -means. In this work, we propose a generic coreset construction framework that formulates the coreset selection as a cardinality-constrained bilevel optimization problem. In contrast to existing approaches, our framework does not require model -specific adaptations and applies to any twice differentiable model, including neural networks. show the effectiveness of our framework for a wide range of models in various settings, including training non -convex models online and batch active learning.

Publication status

published

Editor

Book title

Volume

25

Pages / Article No.

73

Publisher

Microtome Publishing

Event

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

importance sampling; Monte Carlo; Bayesian computation; diagnostics

Organisational unit

Notes

Funding

Related publications and datasets