A multi-fidelity machine learning approach to high throughput materials screening
- Clyde Fare
- Peter Fenner
- et al.
- 2022
- npj Computational Materials
Peter Fenner
Pronouns
He/Him/His
Title
Staff Research Scientist
Bio
Dr Peter Fenner joined IBM Research as a Postdoctoral Research Scientist in 2018 and is part of the IBM Research presence at Science and Technology Facilities Council's (STFC) Daresbury Laboratory. His research mostly focuses on Gaussian Processes and Bayesian Optimisation, and has covered topics such as Multi-Fidelity Bayesian Optimisation, and the application of Homomorphic Encryption to improve privacy in a multi-party Gaussian Process workflow.
Peter recieved his PhD in Mathematics from the University of Manchester in 2018. His thesis focused on Boolean matrix semigroups and various algorithmic and computational problems within these monoids.
Publications
A Principled Method for the Creation of Synthetic Multi-Fidelity Data Sets
- Clyde Fare
- Peter Fenner
- et al.
- 2022
- arXiv
Privacy-preserving gaussian process regression - a modular approach to the application of homomorphic encryption
- Peter Fenner
- Edward O. Pyzer-Knapp
- 2020
- AAAI 2020
Top collaborators
CF
Clyde Fare
Staff Research Scientist AI/ML team.