Cooperative Inverse Decision Theory for Uncertain Preferences

Zachary Robertson, Hantao Zhang, Sanmi Koyejo
Proceedings of The 26th International Conference on Artificial Intelligence and Statistics, PMLR 206:5854-5868, 2023.

Abstract

Inverse decision theory (IDT) aims to learn a performance metric for classification by eliciting expert classifications on examples. However, elicitation in practical settings may require many classifications of potentially ambiguous examples. To improve the efficiency of elicitation, we propose the cooperative inverse decision theory (CIDT) framework as a formalization of the performance metric elicitation problem. In cooperative inverse decision theory, the expert and a machine play a game where both are rewarded according to the expert’s performance metric, but the machine does not initially know what this function is. We show that optimal policies in this framework produce active learning that leads to an exponential improvement in sample complexity over previous work. One of our key findings is that a broad class of sub-optimal experts can be represented as having uncertain preferences. We use this finding to show such experts naturally fit into our proposed framework extending inverse decision theory to efficiently deal with decision data that is sub-optimal due to noise, conflicting experts, or systematic error.

Cite this Paper

BibTeX
@InProceedings{pmlr-v206-robertson23a, title = {Cooperative Inverse Decision Theory for Uncertain Preferences}, author = {Robertson, Zachary and Zhang, Hantao and Koyejo, Sanmi}, booktitle = {Proceedings of The 26th International Conference on Artificial Intelligence and Statistics}, pages = {5854--5868}, year = {2023}, editor = {Ruiz, Francisco and Dy, Jennifer and van de Meent, Jan-Willem}, volume = {206}, series = {Proceedings of Machine Learning Research}, month = {25--27 Apr}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v206/robertson23a/robertson23a.pdf}, url = {https://proceedings.mlr.press/v206/robertson23a.html}, abstract = {Inverse decision theory (IDT) aims to learn a performance metric for classification by eliciting expert classifications on examples. However, elicitation in practical settings may require many classifications of potentially ambiguous examples. To improve the efficiency of elicitation, we propose the cooperative inverse decision theory (CIDT) framework as a formalization of the performance metric elicitation problem. In cooperative inverse decision theory, the expert and a machine play a game where both are rewarded according to the expert’s performance metric, but the machine does not initially know what this function is. We show that optimal policies in this framework produce active learning that leads to an exponential improvement in sample complexity over previous work. One of our key findings is that a broad class of sub-optimal experts can be represented as having uncertain preferences. We use this finding to show such experts naturally fit into our proposed framework extending inverse decision theory to efficiently deal with decision data that is sub-optimal due to noise, conflicting experts, or systematic error.} }
Endnote
%0 Conference Paper %T Cooperative Inverse Decision Theory for Uncertain Preferences %A Zachary Robertson %A Hantao Zhang %A Sanmi Koyejo %B Proceedings of The 26th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2023 %E Francisco Ruiz %E Jennifer Dy %E Jan-Willem van de Meent %F pmlr-v206-robertson23a %I PMLR %P 5854--5868 %U https://proceedings.mlr.press/v206/robertson23a.html %V 206 %X Inverse decision theory (IDT) aims to learn a performance metric for classification by eliciting expert classifications on examples. However, elicitation in practical settings may require many classifications of potentially ambiguous examples. To improve the efficiency of elicitation, we propose the cooperative inverse decision theory (CIDT) framework as a formalization of the performance metric elicitation problem. In cooperative inverse decision theory, the expert and a machine play a game where both are rewarded according to the expert’s performance metric, but the machine does not initially know what this function is. We show that optimal policies in this framework produce active learning that leads to an exponential improvement in sample complexity over previous work. One of our key findings is that a broad class of sub-optimal experts can be represented as having uncertain preferences. We use this finding to show such experts naturally fit into our proposed framework extending inverse decision theory to efficiently deal with decision data that is sub-optimal due to noise, conflicting experts, or systematic error.
APA
Robertson, Z., Zhang, H. & Koyejo, S.. (2023). Cooperative Inverse Decision Theory for Uncertain Preferences. Proceedings of The 26th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 206:5854-5868 Available from https://proceedings.mlr.press/v206/robertson23a.html.

Related Material