5 papers
Data Sharing with Endogenous Choices over Differential Privacy Levels
Raef Bassily, Kate Donahue, Diptangshu Sen +2
Motivated by the rapid push to decentralize sharing of data, we study whether large-scale data sharing coalitions can form in a decentralized manner under differential privacy when…
When to Ask a Question: Understanding Communication Strategies in Generative AI Tools
Charlotte Park, Kate Donahue, Manish Raghavan
Generative AI models differ from traditional machine learning tools in that they allow users to provide as much or as little information as they choose in their inputs. This flexib…
Adaptive Online Mirror Descent for Tchebycheff Scalarization in Multi-Objective Learning
Meitong Liu, Xiaoyuan Zhang, Chulin Xie +2
Multi-objective learning (MOL) aims to learn under multiple potentially conflicting objectives and strike a proper balance. While recent preference-guided MOL methods often rely on…
Human-AI Collaboration with Misaligned Preferences
Jiaxin Song, Parnian Shahkar, Kate Donahue +1
In many real-life settings, algorithms play the role of assistants, while humans ultimately make the final decision. Often, algorithms specifically act as curators, narrowing down…
An Abundance of Katherines: The Game Theory of Baby Naming
Katy Blumer, Kate Donahue, Katie Fritz +5
In this paper, we study the highly competitive arena of baby naming. Through making several Extremely Reasonable Assumptions (namely, that parents are myopic, perfectly knowledgeab…