Adaptive Conformal Prediction Intervals Over Trajectory Ensembles
By: Ruipu Li, Daniel Menacho, Alexander Rodríguez
Potential Business Impact:
Makes predictions more accurate about future events.
Future trajectories play an important role across domains such as autonomous driving, hurricane forecasting, and epidemic modeling, where practitioners commonly generate ensemble paths by sampling probabilistic models or leveraging multiple autoregressive predictors. While these trajectories reflect inherent uncertainty, they are typically uncalibrated. We propose a unified framework based on conformal prediction that transforms sampled trajectories into calibrated prediction intervals with theoretical coverage guarantees. By introducing a novel online update step and an optimization step that captures inter-step dependencies, our method can produce discontinuous prediction intervals around each trajectory, naturally capture temporal dependencies, and yield sharper, more adaptive uncertainty estimates.
Similar Papers
Online Conformal Inference with Retrospective Adjustment for Faster Adaptation to Distribution Shift
Machine Learning (Stat)
Fixes predictions when data changes quickly.
Adaptive Individual Uncertainty under Out-Of-Distribution Shift with Expert-Routed Conformal Prediction
Machine Learning (CS)
Helps drug discovery AI know when it's wrong.
Conformal Prediction and Trustworthy AI
Machine Learning (CS)
Makes AI trustworthy by showing what it knows.