Kernel Identification Through Transformers
This addresses the problem of kernel selection for Gaussian Process models, which is crucial for performance but often slow, by providing a fast automated solution, though it appears incremental as it applies a known deep learning method to a specific domain.
This work tackles the challenge of constructing custom kernel functions for high-dimensional Gaussian Process regression models by introducing KITT, a transformer-based approach that generates kernel recommendations in under 0.1 seconds, which is orders of magnitude faster than conventional methods, and yields strong performance on diverse regression benchmarks.
Kernel selection plays a central role in determining the performance of Gaussian Process (GP) models, as the chosen kernel determines both the inductive biases and prior support of functions under the GP prior. This work addresses the challenge of constructing custom kernel functions for high-dimensional GP regression models. Drawing inspiration from recent progress in deep learning, we introduce a novel approach named KITT: Kernel Identification Through Transformers. KITT exploits a transformer-based architecture to generate kernel recommendations in under 0.1 seconds, which is several orders of magnitude faster than conventional kernel search algorithms. We train our model using synthetic data generated from priors over a vocabulary of known kernels. By exploiting the nature of the self-attention mechanism, KITT is able to process datasets with inputs of arbitrary dimension. We demonstrate that kernels chosen by KITT yield strong performance over a diverse collection of regression benchmarks.