Uncertainty Disentanglement with Non-stationary Heteroscedastic Gaussian Processes for Active Learning
This work addresses uncertainty quantification for active learning applications, but appears incremental as it builds on existing Gaussian process methods.
The authors tackled the problem of disentangling uncertainty in Gaussian processes by proposing a non-stationary heteroscedastic model, which separates overall uncertainty into aleatoric and epistemic components and demonstrates usability in active learning with ablations on multiple datasets.
Gaussian processes are Bayesian non-parametric models used in many areas. In this work, we propose a Non-stationary Heteroscedastic Gaussian process model which can be learned with gradient-based techniques. We demonstrate the interpretability of the proposed model by separating the overall uncertainty into aleatoric (irreducible) and epistemic (model) uncertainty. We illustrate the usability of derived epistemic uncertainty on active learning problems. We demonstrate the efficacy of our model with various ablations on multiple datasets.