Batch Active Learning in Gaussian Process Regression using Derivatives
This work addresses batch active learning for Gaussian Process regression, offering incremental improvements by leveraging derivative information for more efficient data selection.
The paper tackles the problem of selecting batches of data for active learning in Gaussian Process regression by incorporating derivative information, resulting in improved performance across diverse applications as shown in empirical comparisons.
We investigate the use of derivative information for Batch Active Learning in Gaussian Process regression models. The proposed approach employs the predictive covariance matrix for selection of data batches to exploit full correlation of samples. We theoretically analyse our proposed algorithm taking different optimality criteria into consideration and provide empirical comparisons highlighting the advantage of incorporating derivatives information. Our results show the effectiveness of our approach across diverse applications.