Emulating the Expert: Inverse Optimization through Online Learning

Bärmann A, Pokutta S, Schneider O (2017)


Publication Language: English

Publication Type: Conference contribution

Publication year: 2017

Publisher: PMLR

Series: Proceedings of Machine Learning Research

City/Town: International Convention Centre, Sydney, Australia

Book Volume: 70

Pages Range: 400--410

Conference Proceedings Title: Proceedings of the 34th International Conference on Machine Learning (ICML)

URI: 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.

Authors with CRIS profile

Involved external institutions

How to cite

APA:

Bärmann, A., Pokutta, S., & Schneider, O. (2017). Emulating the Expert: Inverse Optimization through Online Learning. In Precup D, Teh YW (Eds.), Proceedings of the 34th International Conference on Machine Learning (ICML) (pp. 400--410). International Convention Centre, Sydney, Australia: PMLR.

MLA:

Bärmann, Andreas, Sebastian Pokutta, and Oskar Schneider. "Emulating the Expert: Inverse Optimization through Online Learning." Proceedings of the Proceedings of the 34th International Conference on Machine Learning (ICML) Ed. Precup D, Teh YW, International Convention Centre, Sydney, Australia: PMLR, 2017. 400--410.

BibTeX: Download