FFDCI trains a feature-based quantile error predictor and then applies an online adaptive offset, claiming asymptotic coverage and shorter intervals than existing conformal baselines on 12 datasets.
The learning rate was 0.001
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Feature Fitted Online Conformal Prediction for Deep Time Series Forecasting Model
FFDCI trains a feature-based quantile error predictor and then applies an online adaptive offset, claiming asymptotic coverage and shorter intervals than existing conformal baselines on 12 datasets.