The LCFI website uses cookies only for anonymised website statistics and for ensuring our security, never for tracking or identifying you individually. To find out more, and to find out how we protect your personal information, please read our privacy policy.

Counterfactual Accuracies of Alternative Models

Workshop Paper by Umang Bhatt, Muhammad Bilal Zafar, Krishna Gummadi, Adrian Weller

Counterfactual Accuracies of Alternative ModelsML-IRL: Machine Learning in Real Life Workshop at ICLR 2020.

Abstract: Typically we fit a model by optimizing performance on training data. Here we focus on the case of a binary classifier that predicts ‘yes’ or ‘no’ for any given test point. We explore a notion of confidence in a particular prediction by asking: If we were to fit an alternative classifier from our model class to the same training data, how much training accuracy would we have to give up so that the prediction for the test point would change?

Download Workshop Paper