Skip to yearly menu bar Skip to main content


Active Surrogate Estimators: An Active Learning Approach to Label-Efficient Model Evaluation

Jannik Kossen · Sebastian Farquhar · Yarin Gal · Thomas Rainforth

Hall J (level 1) #114

Keywords: [ sample-efficiency ] [ bayesian active learning ] [ active evaluation ] [ active testing ] [ model evaluation ] [ Active Learning ] [ experimental design ]


We propose Active Surrogate Estimators (ASEs), a new method for label-efficient model evaluation. Evaluating model performance is a challenging and important problem when labels are expensive. ASEs address this active testing problem using a surrogate-based estimation approach that interpolates the errors of points with unknown labels, rather than forming a Monte Carlo estimator. ASEs actively learn the underlying surrogate, and we propose a novel acquisition strategy, XWED, that tailors this learning to the final estimation task. We find that ASEs offer greater label-efficiency than the current state-of-the-art when applied to challenging model evaluation problems for deep neural networks.

Chat is not available.