Algorithm for kernel-based machine learning
ORAL
Abstract
We present an algorithm that is able to determine the hyperparameters of a kernel-based representation of a machine-learning representation of input-output data. The algorithm is best applied on fully error-corrected quantum machines but can be applied on near-term computers. We present the scaling relationships and potential applications for quantum chemistry and other areas of physics.
*This research was undertaken, in part, thanks to funding from the Canada Research Chairs Program. This work has been supported in part by the Natural Sciences and Engineering Research Council of Canada (NSERC) under grants RGPIN-2023-05510 and DGECR-2023-00026. J.G. acknowledge the NSERC CREATE in Quantum Computing Program (Grant Number 543245).
–
Presenters
-
Thomas E Baker
- University of Victoria