Conformal Prediction for Spatially Dependent Data via Sequential Whitening

Key points

• This assumption may fail under spatial dependence and nonrandom sampling geometry.1
• Existing spatial methods use fitting residuals to remove the predictable part of spatial variation from calibration and target errors.1
• We address this by additionally conditioning on the calibration residuals sequentially, which scales to large networks through nearest-neighbour approximations.1
• We also bound coverage loss under covariance misspecification and develop a diagnostic that identifies regions at risk of undercoverage.1

Sources (1)

• [1]Conformal Prediction for Spatially Dependent Data via Sequential Whitening
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 7, 02:44 PM

  Split conformal prediction uses prediction errors on held-out (calibration) data to determine how wide the prediction intervals should be.

  This assumption may fail under spatial dependence and nonrandom sampling geometry.

Extractive summary: sentences quoted from the sources.