Bayesian Optimization for Dessert

Bayesian Optimization for a Better Dessert Greg Kochanski, Daniel Golovin, John Karro, Benjamin Solnik, Subhodeep Moitra, and D. Sculley {gpk, dgg, karro, bsolnik, smoitra, dsculley}@google.com; Google Brain Team Abstract We present a case study on applying Bayesian Optimization to a complex real-world system; our challenge was to optimize chocolate chip cookies. The process was a mixed-initiative system where both human chefs, human raters, and a machine optimizer participated in 144 experiments. This process resulted in highly rated cookies that deviated from expectations in some surprising ways – much less sugar in California, and cayenne in Pittsburgh. Our experience highlights the importance of incorporating domain expertise and the value of transfer learning approaches.

The image is a mock academic paper titled “Bayesian Optimization for a Better Dessert.” Its abstract humorously presents optimizing chocolate chip cookies as a serious machine-learning research project, including 144 experiments, human chefs and raters, and unexpected regional results such as less sugar in California and cayenne in Pittsburgh. It is shared as a joke about overengineering an ordinary baking problem with advanced technical methods.

• @ithueti / 7702 2022-09-13