no code implementations • 14 Feb 2023 • Tom Yan, Shantanu Gupta, Zachary Lipton
While earlier works cast these manipulations as undesirable gaming, recent works have adopted a more nuanced causal framing in which manipulations can improve outcomes of interest, and setting coherent mechanisms requires accounting for both predictive accuracy and improvement of the outcome.
no code implementations • 16 Jun 2022 • Tom Yan, Chicheng Zhang
The fast spreading adoption of machine learning (ML) by companies across industries poses significant regulatory challenges.
no code implementations • 23 Feb 2022 • Tom Yan, Chicheng Zhang
The growing use of machine learning models in consequential settings has highlighted an important and seemingly irreconcilable tension between transparency and vulnerability to gaming.
no code implementations • NeurIPS 2021 • Ellen Vitercik, Tom Yan
We conclude with an application of our guarantees to multi-task mechanism design, where there are multiple distributions over buyers' values and the goal is to learn a high-revenue mechanism per distribution.
no code implementations • NeurIPS 2020 • Tom Yan, Christian Kroer, Alexander Peysakhovich
We apply our methods to study teams of artificial RL agents as well as real world teams from professional sports.
4 code implementations • 9 Jan 2018 • Mathew Monfort, Alex Andonian, Bolei Zhou, Kandan Ramakrishnan, Sarah Adel Bargal, Tom Yan, Lisa Brown, Quanfu Fan, Dan Gutfruend, Carl Vondrick, Aude Oliva
We present the Moments in Time Dataset, a large-scale human-annotated collection of one million short videos corresponding to dynamic events unfolding within three seconds.