Reproduce “Conformal Prediction for Time-Dependent PDEs” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Joshua Stiller, Annika Schneider, Eyke Hüllermeier
The authors study conformal prediction for evolving PDEs, where time shifts can break coverage because calibration and test states are not exchangeable. They reweight calibration examples using time-specific Gaussian state distributions for linear PDEs with affine numerical schemes. In experiments, WCP Gauss preserves target coverage over time in pulsed thermography, but this result does not guarantee coverage for arbitrary PDEs.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.