Learning from Streaming Data when Users Choose

Jinyan Su, Sarah Dean
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:46772-46803, 2024.

Abstract

In digital markets comprised of many competing services, each user chooses between multiple service providers according to their preferences, and the chosen service makes use of the user data to incrementally improve its model. The service providers’ models influence which service the user will choose at the next time step, and the user’s choice, in return, influences the model update, leading to a feedback loop. In this paper, we formalize the above dynamics and develop a simple and efficient decentralized algorithm to locally minimize the overall user loss. Theoretically, we show that our algorithm asymptotically converges to stationary points of of the overall loss almost surely. We also experimentally demonstrate the utility of our algorithm with real world data.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-su24a, title = {Learning from Streaming Data when Users Choose}, author = {Su, Jinyan and Dean, Sarah}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {46772--46803}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/su24a/su24a.pdf}, url = {https://proceedings.mlr.press/v235/su24a.html}, abstract = {In digital markets comprised of many competing services, each user chooses between multiple service providers according to their preferences, and the chosen service makes use of the user data to incrementally improve its model. The service providers’ models influence which service the user will choose at the next time step, and the user’s choice, in return, influences the model update, leading to a feedback loop. In this paper, we formalize the above dynamics and develop a simple and efficient decentralized algorithm to locally minimize the overall user loss. Theoretically, we show that our algorithm asymptotically converges to stationary points of of the overall loss almost surely. We also experimentally demonstrate the utility of our algorithm with real world data.} }
Endnote
%0 Conference Paper %T Learning from Streaming Data when Users Choose %A Jinyan Su %A Sarah Dean %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-su24a %I PMLR %P 46772--46803 %U https://proceedings.mlr.press/v235/su24a.html %V 235 %X In digital markets comprised of many competing services, each user chooses between multiple service providers according to their preferences, and the chosen service makes use of the user data to incrementally improve its model. The service providers’ models influence which service the user will choose at the next time step, and the user’s choice, in return, influences the model update, leading to a feedback loop. In this paper, we formalize the above dynamics and develop a simple and efficient decentralized algorithm to locally minimize the overall user loss. Theoretically, we show that our algorithm asymptotically converges to stationary points of of the overall loss almost surely. We also experimentally demonstrate the utility of our algorithm with real world data.
APA
Su, J. & Dean, S.. (2024). Learning from Streaming Data when Users Choose. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:46772-46803 Available from https://proceedings.mlr.press/v235/su24a.html.

Related Material