A Stepwise uncertainty reduction approach to constrained global optimization

Victor Picheny
Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics, PMLR 33:787-795, 2014.

Abstract

Using statistical emulators to guide sequential evaluations of complex computer experiments is now a well-established practice. When a model provides multiple outputs, a typical objective is to optimize one of the outputs with constraints (for instance, a threshold not to exceed) on the values of the other outputs. We propose here a new optimization strategy based on the stepwise uncertainty reduction paradigm, which offers an efficient trade-off between exploration and local search near the boundaries. The strategy is illustrated on numerical examples.

Cite this Paper

BibTeX
@InProceedings{pmlr-v33-picheny14, title = {{A Stepwise uncertainty reduction approach to constrained global optimization}}, author = {Picheny, Victor}, booktitle = {Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics}, pages = {787--795}, year = {2014}, editor = {Kaski, Samuel and Corander, Jukka}, volume = {33}, series = {Proceedings of Machine Learning Research}, address = {Reykjavik, Iceland}, month = {22--25 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v33/picheny14.pdf}, url = {https://proceedings.mlr.press/v33/picheny14.html}, abstract = {Using statistical emulators to guide sequential evaluations of complex computer experiments is now a well-established practice. When a model provides multiple outputs, a typical objective is to optimize one of the outputs with constraints (for instance, a threshold not to exceed) on the values of the other outputs. We propose here a new optimization strategy based on the stepwise uncertainty reduction paradigm, which offers an efficient trade-off between exploration and local search near the boundaries. The strategy is illustrated on numerical examples.} }
Endnote
%0 Conference Paper %T A Stepwise uncertainty reduction approach to constrained global optimization %A Victor Picheny %B Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2014 %E Samuel Kaski %E Jukka Corander %F pmlr-v33-picheny14 %I PMLR %P 787--795 %U https://proceedings.mlr.press/v33/picheny14.html %V 33 %X Using statistical emulators to guide sequential evaluations of complex computer experiments is now a well-established practice. When a model provides multiple outputs, a typical objective is to optimize one of the outputs with constraints (for instance, a threshold not to exceed) on the values of the other outputs. We propose here a new optimization strategy based on the stepwise uncertainty reduction paradigm, which offers an efficient trade-off between exploration and local search near the boundaries. The strategy is illustrated on numerical examples.
RIS
TY - CPAPER TI - A Stepwise uncertainty reduction approach to constrained global optimization AU - Victor Picheny BT - Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics DA - 2014/04/02 ED - Samuel Kaski ED - Jukka Corander ID - pmlr-v33-picheny14 PB - PMLR DP - Proceedings of Machine Learning Research VL - 33 SP - 787 EP - 795 L1 - http://proceedings.mlr.press/v33/picheny14.pdf UR - https://proceedings.mlr.press/v33/picheny14.html AB - Using statistical emulators to guide sequential evaluations of complex computer experiments is now a well-established practice. When a model provides multiple outputs, a typical objective is to optimize one of the outputs with constraints (for instance, a threshold not to exceed) on the values of the other outputs. We propose here a new optimization strategy based on the stepwise uncertainty reduction paradigm, which offers an efficient trade-off between exploration and local search near the boundaries. The strategy is illustrated on numerical examples. ER -
APA
Picheny, V.. (2014). A Stepwise uncertainty reduction approach to constrained global optimization. Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 33:787-795 Available from https://proceedings.mlr.press/v33/picheny14.html.

Related Material