Combining multitask and transfer learning with deep Gaussian processes for autotuning-based performance engineering

TitleCombining multitask and transfer learning with deep Gaussian processes for autotuning-based performance engineering
Publication TypeJournal Article
Year of Publication2023
AuthorsLuszczek, P., W. M. Sid-Lakhdar, and J. Dongarra
JournalThe International Journal of High Performance Computing Applications
Date Published2023-03
ISSN1094-3420
Abstract

We combine deep Gaussian processes (DGPs) with multitask and transfer learning for the performance modeling and optimization of HPC applications. Deep Gaussian processes merge the uncertainty quantification advantage of Gaussian processes (GPs) with the predictive power of deep learning. Multitask and transfer learning allow for improved learning efficiency when several similar tasks are to be learned simultaneously and when previous learned models are sought to help in the learning of new tasks, respectively. A comparison with state-of-the-art autotuners shows the advantage of our approach on two application problems. In this article, we combine DGPs with multitask and transfer learning to allow for both an improved tuning of an application parameters on problems of interest but also the prediction of parameters on any potential problem the application might encounter.

URLhttp://journals.sagepub.com/doi/10.1177/10943420231166365
DOI10.1177/10943420231166365
Short TitleThe International Journal of High Performance Computing Applications
External Publication Flag: