Year: 2026
Type: article
Abstract: . We consider the problem of selecting a subset of points from a dataset of [Formula: see text] unlabeled examples for labeling, with the goal of training a multiclass classifier. To address this, we build upon the regret minimization framework introduced by Allen-Zhu et al. [ Near-optimal design of experiments via regret minimization, in Proceedings of the 34th International Conference on Machine Learning, PMLR 70, 2017, pp. 126–135]. We propose an alternative regularization scheme within this framework, which leads to a new sample selection objective along with a provable sample complexity bound that guarantees a [Formula: see text]-approximate solution. Additionally, we extend the regret minimization approach to handle experimental design in the ridge regression setting. We evaluate the selected samples using logistic regression and compare performance against several state-of-the-art methods. Our empirical results on MNIST, CIFAR-10, and a 50-class subset of ImageNet demonstrate that our method consistently outperforms competing approaches across most scenarios.
DOI: 10.1137/25m1753097
Authors: Youguang Chen, George Biros
Institution: The University of Texas at Austin
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7165728385