Identifying Preferences Is Harder Than You Think

Discover how a simple "organize-then-vote" step transforms choice overload into confident, authentic decisions.

Adversarial Machine UNlearning (AMUN)

We present AMUN, a new method for machine unlearning that leverages adversarial examples to remove specific training samples from a model while preserving accuracy. Our approach outperforms prior state-of-the-art unlearning methods, especially when access to remaining training data is limited.

Algorithmic Collective Action With Two Collectives

Many socio-technical systems rely on user interactions and information to recommend content to other users. Here we study how collectives of users may act together to influence these systems.

Private Prices

We discuss a method for helping users find better prices in online markets with personalized pricing. We will discuss how trading might benefit users and under what circumstances trading is likely to occur.