Bayesian optimization and design of experiments

Synopsis

Bayesian optimization is a popular machine learning-based approach for optimizing black-box functions, with successful applications including hyperparameter tuning of machine learning algorithms, design of engineering systems, and sensor set selection. After introducing Bayesian optimization, we present some joint research with the BASF Data Science for Materials & Chemistry teams. With BASF, we’re interested to solve Bayesian optimization challenges which may simultaneously exhibit: multiple objectives, mixed-feature spaces, asynchronous decisions, large batch sizes, input constraints, multi-fidelity observations, hierarchical choices, and costs associated with switching between experimental points. We discuss the machine learning contributions that we’ve found useful towards achieving these goals.

Speaker

Professor Ruth Misener

Imperial College London

Professor Ruth Misener is the BASF/RAEng Research Chair in Data-Driven Optimisation (2022-27) at the Imperial Department of Computing. She previously held an EPSRC Early Career Fellowship (2017-22) and an RAEng Research Fellowship (2012-17). Foundations of her research are in numerical optimisation and computational software. Her applications focus on optimisation challenges arising in industry, e.g. scheduling in manufacturing or experimental design in chemicals research. Ruth also works at the interface of operations research and machine learning. Ruth received the 2017 Sir George Macfarlane Medal as the overall winner of the RAEng Engineers Trust Young Engineer of the Year Award.

Fees

Booking Process/Deadlines

Booking terms and conditions

Contact

Conference Team

Tel: +44 (0)20 7598 1561

Email: conferences@soci.org