Sequential Preference-Based Optimization

01/09/2018

∙

by   Ian Dewancker, et al.

∙

0

∙

share

Many real-world engineering problems rely on human preferences to guide their design and optimization. We present PrefOpt, an open source package to simplify sequential optimization tasks that incorporate human preference feedback. Our approach extends an existing latent variable model for binary preferences to allow for observations of equivalent preference from users.