activity
20242026
most citedTheoretical Foundations of Conformal Prediction

8 citations · 9 across the 3 of their papers we have counts for

collaborators
Showing 2024Show all

6 papers · 1 filter

cs.LG2024

Label Noise Robustness of Conformal Prediction

Bat-Sheva Einbinder, Shai Feldman, Stephen Bates +3

We study the robustness of conformal prediction, a powerful tool for uncertainty quantification, to label noise. Our analysis tackles both regression and classification problems, c…

cs.LG2024

How to Evaluate Reward Models for RLHF

Evan Frick, Tianle Li, Connor Chen +6

We introduce a new benchmark for reward models that quantifies their ability to produce strong language models through RLHF (Reinforcement Learning from Human Feedback). The gold-s…

stat.ML2024

Online conformal prediction with decaying step sizes

Anastasios N. Angelopoulos, Rina Foygel Barber, Stephen Bates

We introduce a method for online conformal prediction with decaying step sizes. Like previous methods, ours possesses a retrospective guarantee of coverage for arbitrary sequences.…

stat.ML2024

Conformal Decision Theory: Safe Autonomous Decisions from Imperfect Predictions

Jordan Lekeufack, Anastasios N. Angelopoulos, Andrea Bajcsy +2

We introduce Conformal Decision Theory, a framework for producing safe autonomous decisions despite imperfect machine learning predictions. Examples of such decisions are ubiquitou…

stat.ME2024

Data-Adaptive Tradeoffs among Multiple Risks in Distribution-Free Prediction

Drew T. Nguyen, Reese Pathak, Anastasios N. Angelopoulos +2

Decision-making pipelines are generally characterized by tradeoffs among various risk functions. It is often desirable to manage such tradeoffs in a data-adaptive manner. As we dem…

stat.ML2024

PPI++: Efficient Prediction-Powered Inference

Anastasios N. Angelopoulos, John C. Duchi, Tijana Zrnic

We present PPI++: a computationally lightweight methodology for estimation and inference based on a small labeled dataset and a typically much larger dataset of machine-learning pr…