Adaptive representation of molecules and materials in Bayesian optimization
Mahyar Rajabi Kochi, Negareh Mahboubi, Aseem Partap Singh Gill, Seyed Mohamad Moosavi
Abstract
, when missing key features, can adversely impact BO performance, highlighting the importance of starting from a full feature set and adapt it to different tasks. Our findings highlight FABO as a robust approach for navigating large, complex materials search spaces in automated discovery campaigns.
Topics & Concepts
Bayesian optimizationRepresentation (politics)Bayesian probabilityComputer scienceMoleculeChemistryTheoretical computer scienceNanotechnologyArtificial intelligenceMaterials scienceOrganic chemistryPolitical scienceLawPoliticsMachine Learning in Materials ScienceComputational Drug Discovery MethodsMachine Learning and Algorithms