Transductive Active Learning: Theory and Applications

Hübotter, Jonas, Sukhija, Bhavya, Treven, Lenart, As, Yarden, Krause, Andreas

arXiv.org Artificial Intelligence 

We generalize active learning to address real-world settings with concrete prediction targets where sampling is restricted to an accessible region of the domain, while prediction targets may lie outside this region. We analyze a family of decision rules that sample adaptively to minimize uncertainty about prediction targets. We are the first to show, under general regularity assumptions, that such decision rules converge uniformly to the smallest possible uncertainty obtainable from the accessible data. We demonstrate their strong sample efficiency in two key applications: Active few-shot fine-tuning of large neural networks and safe Bayesian optimization, where they improve significantly upon the state-of-the-art.

Duplicate Docs Excel Report

Title
None found

Similar Docs  Excel Report  more

TitleSimilaritySource
None found