Emulating the Expert: Inverse Optimization through Online Learning

Andreas Bärmann, Sebastian Pokutta, Oskar Schneider
Proceedings of the 34th International Conference on Machine Learning, PMLR 70:400-410, 2017.

Abstract

In this paper, we demonstrate how to learn the objective function of a decision maker while only observing the problem input data and the decision maker’s corresponding decisions over multiple rounds. Our approach is based on online learning techniques and works for linear objectives over arbitrary sets for which we have a linear optimization oracle and as such generalizes previous work based on KKT-system decomposition and dualization approaches. The applicability of our framework for learning linear constraints is also discussed briefly. Our algorithm converges at a rate of O(1/sqrt(T)), and we demonstrate its effectiveness and applications in preliminary computational results.

Cite this Paper


BibTeX
@InProceedings{pmlr-v70-barmann17a, title = {Emulating the Expert: Inverse Optimization through Online Learning}, author = {Andreas B{\"a}rmann and Sebastian Pokutta and Oskar Schneider}, booktitle = {Proceedings of the 34th International Conference on Machine Learning}, pages = {400--410}, year = {2017}, editor = {Precup, Doina and Teh, Yee Whye}, volume = {70}, series = {Proceedings of Machine Learning Research}, month = {06--11 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v70/barmann17a/barmann17a.pdf}, url = { http://proceedings.mlr.press/v70/barmann17a.html }, abstract = {In this paper, we demonstrate how to learn the objective function of a decision maker while only observing the problem input data and the decision maker’s corresponding decisions over multiple rounds. Our approach is based on online learning techniques and works for linear objectives over arbitrary sets for which we have a linear optimization oracle and as such generalizes previous work based on KKT-system decomposition and dualization approaches. The applicability of our framework for learning linear constraints is also discussed briefly. Our algorithm converges at a rate of O(1/sqrt(T)), and we demonstrate its effectiveness and applications in preliminary computational results.} }
Endnote
%0 Conference Paper %T Emulating the Expert: Inverse Optimization through Online Learning %A Andreas Bärmann %A Sebastian Pokutta %A Oskar Schneider %B Proceedings of the 34th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2017 %E Doina Precup %E Yee Whye Teh %F pmlr-v70-barmann17a %I PMLR %P 400--410 %U http://proceedings.mlr.press/v70/barmann17a.html %V 70 %X In this paper, we demonstrate how to learn the objective function of a decision maker while only observing the problem input data and the decision maker’s corresponding decisions over multiple rounds. Our approach is based on online learning techniques and works for linear objectives over arbitrary sets for which we have a linear optimization oracle and as such generalizes previous work based on KKT-system decomposition and dualization approaches. The applicability of our framework for learning linear constraints is also discussed briefly. Our algorithm converges at a rate of O(1/sqrt(T)), and we demonstrate its effectiveness and applications in preliminary computational results.
APA
Bärmann, A., Pokutta, S. & Schneider, O.. (2017). Emulating the Expert: Inverse Optimization through Online Learning. Proceedings of the 34th International Conference on Machine Learning, in Proceedings of Machine Learning Research 70:400-410 Available from http://proceedings.mlr.press/v70/barmann17a.html .

Related Material