Abstract
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.
Original language | English |
---|---|
Pages (from-to) | 11-21 |
Number of pages | 11 |
Journal | Proceedings of Machine Learning Research |
Volume | 216 |
State | Published - 2023 |
Event | 39th Conference on Uncertainty in Artificial Intelligence, UAI 2023 - Pittsburgh, United States Duration: 31 Jul 2023 → 4 Aug 2023 |
All Science Journal Classification (ASJC) codes
- Artificial Intelligence
- Software
- Control and Systems Engineering
- Statistics and Probability