front matter
As the complexity of problems we face in machine learning and related fields continues to increase, it is more and more important to optimize our use of resources and make informed decisions efficiently. Bayesian optimization, a powerful technique for finding the maxima and minima of objective functions that are expensive to evaluate, has emerged as a very useful solution to this challenge. One reason is that the function can be taken as a black box, which enables researchers and practitioners to tackle very complicated functions with Bayesian inference as the main method of optimization.
Due to its complexity, Bayesian optimization has been more out of reach for beginner ML practitioners than other methods. However, a tool like Bayesian optimization must be in the toolkit of any ML practitioner who wants to get the best results. To master this topic, one must have a very solid intuition of calculus and probability.
This is where Bayesian Optimization in Action comes to the rescue. In this book, Quan beautifully and successfully demystifies these complex concepts. Using a hands-on approach, clear diagrams, real-world examples, and useful code examples, he lifts the veil off the complexities of the topic, both from the theoretical and the practical point of view.