Title: Bayesian Optimization in Molecule Space: Challenges and Opportunities
Speaker: Austin Tripp
Affiliation: University of Cambridge
Location: Huxley 315

Abstract. Rational design of experiments in chemistry is one of the most commonly mentioned applications of Bayesian optimization (BO). Therefore you might presume that existing BO algorithms for chemistry are well-developed. In this talk I explain how performing BO on the discrete, structured space of molecules introduces extra complexity to BO which standard methods do not handle well. I will outline specific problems and potential avenues for solving them, in addition to covering some recent work in this area. All are welcome, but the target audience for this talk is optimization researchers interested in the fundamental algorithmic problems which chemistry applications present.

Biography. Austin Tripp is a final-year PhD student at Cambridge researching ML methods for molecules. More info on his website austintripp.ca