On the convergence of loss and uncertainty-based active learning algorithms

arXiv:2312.13927v2 Announce Type: replace
Abstract: We consider the convergence rates of loss and uncertainty-based active learning algorithms under various assumptions. Firstly, we establish a set of conditions that ensure convergence rates when applied to linear classifiers and linearly separable datasets. This includes demonstrating convergence rate guarantees for loss-based sampling with various loss functions. Secondly, we introduce a framework that allows us to derive convergence rate bounds for loss-based sampling by leveraging known convergence rate bounds for stochastic gradient descent algorithms. …

abstract active learning algorithms arxiv assumptions classifiers convergence cs.ai cs.lg datasets linear loss rate sampling set type uncertainty