Speaker "Scott Clark" Details Back
-
Name
Scott Clark
-
Company
Sigopt
-
Designation
CEO
Topic
Using Bayesian Optimization to Tune Machine Learning Models
Abstract
We introduce Bayesian Global Optimization, the core technology behind SigOpt, as an efficient way to optimize machine learning model parameters, especially when evaluating different parameters is time-consuming or expensive. The techniques described can be used to help tackle any number of machine learning optimization problems, like tuning a deep learning model, classification algorithm, or any other machine learning system. In this talk we will build motivation, explain the underlying techniques, and give examples and comparisons to other standard methods.