1 code implementation • 7 Nov 2020 • Karl Krauth, Sarah Dean, Alex Zhao, Wenshuo Guo, Mihaela Curmei, Benjamin Recht, Michael I. Jordan
We observe that offline metrics are correlated with online performance over a range of environments.
1 code implementation • 30 Jun 2021 • Mihaela Curmei, Sarah Dean, Benjamin Recht
In this work, we consider how preference models in interactive recommendation systems determine the availability of content and users' opportunities for discovery.
1 code implementation • 6 Jun 2022 • Sarah Dean, Mihaela Curmei, Lillian J. Ratliff, Jamie Morgenstern, Maryam Fazel
We study the participation and retraining dynamics that arise when both the learners and sub-populations of users are \emph{risk-reducing}, which cover a broad class of updates including gradient descent, multiplicative weights, etc.
no code implementations • 1 Aug 2022 • Mihaela Curmei, Andreas Haupt, Dylan Hadfield-Menell, Benjamin Recht
Second, we discuss implications of dynamic preference models for recommendation systems evaluation and design.
no code implementations • 17 Mar 2023 • Han Zhang, Shangen Lu, Yixin Wang, Mihaela Curmei
Moreover, we show that the effects of recommendations can persist in networks, in part due to their indirect impacts on natural dynamics even after recommendations are turned off.
no code implementations • 17 Sep 2023 • Mihaela Curmei, Walid Krichene, Li Zhang, Mukund Sundararajan
It can be applied to different types of public item data, including: (1) categorical item features; (2) item-item similarities learned from public sources; and (3) publicly available user feedback.
no code implementations • 19 Dec 2023 • Avinandan Bose, Mihaela Curmei, Daniel L. Jiang, Jamie Morgenstern, Sarah Dean, Lillian J. Ratliff, Maryam Fazel
(ii) Suboptimal Local Solutions: The total loss (sum of loss functions across all users and all services) landscape is not convex even if the individual losses on a single service are convex, making it likely for the learning dynamics to get stuck in local minima.