Guided Deep Kernel Learning
This addresses the challenge of maintaining Bayesian advantages in deep kernel learning for machine learning practitioners, though it is incremental as it builds on existing DKL and NNGP methods.
The paper tackles the problem of deep kernel learning (DKL) losing Bayesian benefits like uncertainty estimation by proposing a method that uses infinite-width neural networks (NNGP) to guide DKL optimization, resulting in robust overfitting resistance, good predictive performance, and reliable uncertainty estimations on multiple benchmark datasets.
Combining Gaussian processes with the expressive power of deep neural networks is commonly done nowadays through deep kernel learning (DKL). Unfortunately, due to the kernel optimization process, this often results in losing their Bayesian benefits. In this study, we present a novel approach for learning deep kernels by utilizing infinite-width neural networks. We propose to use the Neural Network Gaussian Process (NNGP) model as a guide to the DKL model in the optimization process. Our approach harnesses the reliable uncertainty estimation of the NNGPs to adapt the DKL target confidence when it encounters novel data points. As a result, we get the best of both worlds, we leverage the Bayesian behavior of the NNGP, namely its robustness to overfitting, and accurate uncertainty estimation, while maintaining the generalization abilities, scalability, and flexibility of deep kernels. Empirically, we show on multiple benchmark datasets of varying sizes and dimensionality, that our method is robust to overfitting, has good predictive performance, and provides reliable uncertainty estimations.