Existing approaches to inference in DGP models assume approximate posteriors that force independence between the layers, and do not work well in practice.
Despite advances in scalable models, the inference tools used for Gaussian processes (GPs) have yet to fully capitalize on developments in computing hardware.
Defending Machine Learning models involves certifying and verifying model robustness and model hardening with approaches such as pre-processing inputs, augmenting training data with adversarial samples, and leveraging runtime detection methods to flag any inputs that might have been modified by an adversary.
Bayesian optimization has proven to be a highly effective methodology for the global optimization of unknown, expensive and multimodal functions.
One obstacle to the use of Gaussian processes (GPs) in large-scale problems, and as a component in deep learning system, is the need for bespoke derivations and implementations for small variations in the model or inference.
A longstanding goal in deep learning research has been to precisely characterize training and generalization.