Calibrated Prediction with Covariate Shift via Unsupervised Domain Adaptation
This addresses the issue of overconfident predictions in autonomous agents or human decision-makers when faced with distribution shifts, representing an incremental improvement in uncertainty calibration techniques.
The paper tackles the problem of reliable uncertainty estimation under covariate shift, where real-world data differs from training data, by proposing an algorithm that uses importance weighting and domain adaptation to calibrate predictions, showing it outperforms existing methods in empirical evaluations.
Reliable uncertainty estimates are an important tool for helping autonomous agents or human decision makers understand and leverage predictive models. However, existing approaches to estimating uncertainty largely ignore the possibility of covariate shift--i.e., where the real-world data distribution may differ from the training distribution. As a consequence, existing algorithms can overestimate certainty, possibly yielding a false sense of confidence in the predictive model. We propose an algorithm for calibrating predictions that accounts for the possibility of covariate shift, given labeled examples from the training distribution and unlabeled examples from the real-world distribution. Our algorithm uses importance weighting to correct for the shift from the training to the real-world distribution. However, importance weighting relies on the training and real-world distributions to be sufficiently close. Building on ideas from domain adaptation, we additionally learn a feature map that tries to equalize these two distributions. In an empirical evaluation, we show that our proposed approach outperforms existing approaches to calibrated prediction when there is covariate shift.