POGO uses multi-portfolio wealth maximization to produce a single sequence of radii that achieve the strongest known finite-time group-conditional coverage without any learning-rate hyperparameter.
Bellman conformal inference: Calibrating prediction intervals for time series.arXiv preprint arXiv:2402.05203
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
Bellman calibration supplies a new reliability criterion and post-hoc recalibration method for value functions in offline RL, with finite-sample guarantees at one-dimensional nonparametric rates that avoid Bellman completeness and realizability assumptions.
Proposes Cost-Aware Adaptive Conformal Inference framework providing dual statistical guarantees on long-run violation frequency and cumulative violation cost for runtime assurance in dynamic environments.
citing papers explorer
-
Parameter-Free and Group Conditional Online Conformal Prediction
POGO uses multi-portfolio wealth maximization to produce a single sequence of radii that achieve the strongest known finite-time group-conditional coverage without any learning-rate hyperparameter.
-
Bellman Calibration for $V$-Learning in Offline Reinforcement Learning
Bellman calibration supplies a new reliability criterion and post-hoc recalibration method for value functions in offline RL, with finite-sample guarantees at one-dimensional nonparametric rates that avoid Bellman completeness and realizability assumptions.
-
Cost-Aware Adaptive Conformal Inference for Runtime Assurance in Dynamic Environments
Proposes Cost-Aware Adaptive Conformal Inference framework providing dual statistical guarantees on long-run violation frequency and cumulative violation cost for runtime assurance in dynamic environments.