Data Summarization via Bilevel Optimization

by   Zalán Borsos, et al.

The increasing availability of massive data sets poses a series of challenges for machine learning. Prominent among these is the need to learn models under hardware or human resource constraints. In such resource-constrained settings, a simple yet powerful approach is to operate 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. We 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.



There are no comments yet.


page 16

page 20


Coresets via Bilevel Optimization for Continual Learning and Streaming

Coresets are small data summaries that are sufficient for model training...

Dimension Independent Generalization Error with Regularized Online Optimization

One classical canon of statistics is that large models are prone to over...

Online Supervised Subspace Tracking

We present a framework for supervised subspace tracking, when there are ...

Constrained Machine Learning: The Bagel Framework

Machine learning models are widely used for real-world applications, suc...

GLISTER: Generalization based Data Subset Selection for Efficient and Robust Learning

Large scale machine learning and deep models are extremely data-hungry. ...

Data Sketching for Faster Training of Machine Learning Models

Many machine learning problems reduce to the problem of minimizing an ex...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.