Multi-attribute Bayesian optimization with interactive preference learning

Raul Astudillo, Peter Frazier
Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics, PMLR 108:4496-4507, 2020.

Abstract

We consider black-box global optimization of time-consuming-to-evaluate functions on behalf of a decision-maker (DM) whose preferences must be learned. Each feasible design is associated with a time-consuming-to-evaluate vector of attributes and each vector of attributes is assigned a utility by the DM’s utility function, which may be learned approximately using preferences expressed over pairs of attribute vectors. Past work has used a point estimate of this utility function as if it were error-free within single-objective optimization. However, utility estimation errors may yield a poor suggested design. Furthermore, this approach produces a single suggested ‘best’ design, whereas DMs often prefer to choose from a menu. We propose a novel multi-attribute Bayesian optimization with preference learning approach. Our approach acknowledges the uncertainty in preference estimation and implicitly chooses designs to evaluate that are good not just for a single estimated utility function but a range of likely ones. The outcome of our approach is a menu of designs and evaluated attributes from which the DM makes a final selection. We demonstrate the value and flexibility of our approach in a variety of experiments.

Cite this Paper

BibTeX
@InProceedings{pmlr-v108-astudillo20a, title = {Multi-attribute Bayesian optimization with interactive preference learning}, author = {Astudillo, Raul and Frazier, Peter}, booktitle = {Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics}, pages = {4496--4507}, year = {2020}, editor = {Chiappa, Silvia and Calandra, Roberto}, volume = {108}, series = {Proceedings of Machine Learning Research}, month = {26--28 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v108/astudillo20a/astudillo20a.pdf}, url = {https://proceedings.mlr.press/v108/astudillo20a.html}, abstract = {We consider black-box global optimization of time-consuming-to-evaluate functions on behalf of a decision-maker (DM) whose preferences must be learned. Each feasible design is associated with a time-consuming-to-evaluate vector of attributes and each vector of attributes is assigned a utility by the DM’s utility function, which may be learned approximately using preferences expressed over pairs of attribute vectors. Past work has used a point estimate of this utility function as if it were error-free within single-objective optimization. However, utility estimation errors may yield a poor suggested design. Furthermore, this approach produces a single suggested ‘best’ design, whereas DMs often prefer to choose from a menu. We propose a novel multi-attribute Bayesian optimization with preference learning approach. Our approach acknowledges the uncertainty in preference estimation and implicitly chooses designs to evaluate that are good not just for a single estimated utility function but a range of likely ones. The outcome of our approach is a menu of designs and evaluated attributes from which the DM makes a final selection. We demonstrate the value and flexibility of our approach in a variety of experiments. } }
Endnote
%0 Conference Paper %T Multi-attribute Bayesian optimization with interactive preference learning %A Raul Astudillo %A Peter Frazier %B Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2020 %E Silvia Chiappa %E Roberto Calandra %F pmlr-v108-astudillo20a %I PMLR %P 4496--4507 %U https://proceedings.mlr.press/v108/astudillo20a.html %V 108 %X We consider black-box global optimization of time-consuming-to-evaluate functions on behalf of a decision-maker (DM) whose preferences must be learned. Each feasible design is associated with a time-consuming-to-evaluate vector of attributes and each vector of attributes is assigned a utility by the DM’s utility function, which may be learned approximately using preferences expressed over pairs of attribute vectors. Past work has used a point estimate of this utility function as if it were error-free within single-objective optimization. However, utility estimation errors may yield a poor suggested design. Furthermore, this approach produces a single suggested ‘best’ design, whereas DMs often prefer to choose from a menu. We propose a novel multi-attribute Bayesian optimization with preference learning approach. Our approach acknowledges the uncertainty in preference estimation and implicitly chooses designs to evaluate that are good not just for a single estimated utility function but a range of likely ones. The outcome of our approach is a menu of designs and evaluated attributes from which the DM makes a final selection. We demonstrate the value and flexibility of our approach in a variety of experiments.
APA
Astudillo, R. & Frazier, P.. (2020). Multi-attribute Bayesian optimization with interactive preference learning. Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 108:4496-4507 Available from https://proceedings.mlr.press/v108/astudillo20a.html.

Related Material