7 papers
Anytime Detection of Strategic Deviations in Multi-Agent Systems
Etienne Gauthier, Francis Bach, Michael I. Jordan
In many multi-agent systems, agents interact repeatedly and are expected to settle into stable, rational behavior over time. Yet in practice, behavior often drifts, and detecting s…
Explaining and Preventing Alignment Collapse in Iterative RLHF
Etienne Gauthier, Francis Bach, Michael I. Jordan
Reinforcement learning from human feedback (RLHF) typically assumes a static or non-strategic reward model (RM). In iterative deployment, however, the policy generates the data on…
Adaptive Coverage Policies in Conformal Prediction
Etienne Gauthier, Francis Bach, Michael I. Jordan
Traditional conformal prediction methods construct prediction sets such that the true label falls within the set with a user-specified coverage level. However, poorly chosen covera…
Post-Hoc Large-Sample Statistical Inference
Ben Chugg, Etienne Gauthier, Michael I. Jordan +2
We derive inferential procedures for large sample sizes that remain valid under data-dependent significance levels (so-called "post-hoc valid inference"). Classical statistical too…
Backward Conformal Prediction
Etienne Gauthier, Francis Bach, Michael I. Jordan
We introduce , a method that guarantees conformal coverage while providing flexible control over the size of prediction sets. Unlike standar…
Statistical Collusion by Collectives on Learning Platforms
Etienne Gauthier, Francis Bach, Michael I. Jordan
As platforms increasingly rely on learning algorithms, collectives may form and seek ways to influence these platforms to align with their own interests. This can be achieved by co…