Outside the Echo Chamber: Optimizing the Performative Risk

John P Miller, Juan C Perdomo, Tijana Zrnic
Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7710-7720, 2021.

Abstract

In performative prediction, predictions guide decision-making and hence can influence the distribution of future data. To date, work on performative prediction has focused on finding performatively stable models, which are the fixed points of repeated retraining. However, stable solutions can be far from optimal when evaluated in terms of the performative risk, the loss experienced by the decision maker when deploying a model. In this paper, we shift attention beyond performative stability and focus on optimizing the performative risk directly. We identify a natural set of properties of the loss function and model-induced distribution shift under which the performative risk is convex, a property which does not follow from convexity of the loss alone. Furthermore, we develop algorithms that leverage our structural assumptions to optimize the performative risk with better sample efficiency than generic methods for derivative-free convex optimization.

Cite this Paper

BibTeX
@InProceedings{pmlr-v139-miller21a, title = {Outside the Echo Chamber: Optimizing the Performative Risk}, author = {Miller, John P and Perdomo, Juan C and Zrnic, Tijana}, booktitle = {Proceedings of the 38th International Conference on Machine Learning}, pages = {7710--7720}, year = {2021}, editor = {Meila, Marina and Zhang, Tong}, volume = {139}, series = {Proceedings of Machine Learning Research}, month = {18--24 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v139/miller21a/miller21a.pdf}, url = {https://proceedings.mlr.press/v139/miller21a.html}, abstract = {In performative prediction, predictions guide decision-making and hence can influence the distribution of future data. To date, work on performative prediction has focused on finding performatively stable models, which are the fixed points of repeated retraining. However, stable solutions can be far from optimal when evaluated in terms of the performative risk, the loss experienced by the decision maker when deploying a model. In this paper, we shift attention beyond performative stability and focus on optimizing the performative risk directly. We identify a natural set of properties of the loss function and model-induced distribution shift under which the performative risk is convex, a property which does not follow from convexity of the loss alone. Furthermore, we develop algorithms that leverage our structural assumptions to optimize the performative risk with better sample efficiency than generic methods for derivative-free convex optimization.} }
Endnote
%0 Conference Paper %T Outside the Echo Chamber: Optimizing the Performative Risk %A John P Miller %A Juan C Perdomo %A Tijana Zrnic %B Proceedings of the 38th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2021 %E Marina Meila %E Tong Zhang %F pmlr-v139-miller21a %I PMLR %P 7710--7720 %U https://proceedings.mlr.press/v139/miller21a.html %V 139 %X In performative prediction, predictions guide decision-making and hence can influence the distribution of future data. To date, work on performative prediction has focused on finding performatively stable models, which are the fixed points of repeated retraining. However, stable solutions can be far from optimal when evaluated in terms of the performative risk, the loss experienced by the decision maker when deploying a model. In this paper, we shift attention beyond performative stability and focus on optimizing the performative risk directly. We identify a natural set of properties of the loss function and model-induced distribution shift under which the performative risk is convex, a property which does not follow from convexity of the loss alone. Furthermore, we develop algorithms that leverage our structural assumptions to optimize the performative risk with better sample efficiency than generic methods for derivative-free convex optimization.
APA
Miller, J.P., Perdomo, J.C. & Zrnic, T.. (2021). Outside the Echo Chamber: Optimizing the Performative Risk. Proceedings of the 38th International Conference on Machine Learning, in Proceedings of Machine Learning Research 139:7710-7720 Available from https://proceedings.mlr.press/v139/miller21a.html.

Related Material