AI Paper Atlas

Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes

Deconditional Downscaling with Gaussian Processes

Siu Lun Chau, Shahine Bouabid, Dino Sejdinovic

NeurIPS 2021 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: PAC-Bayes and decoupled GP learning · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use CMP-based VarCMP instead of VBAGGbag-level downscaling · Swiss roll, direct matchingRMSE: 0.22 -> 0.18Improved
use CMP instead of BAGG-GPbag GP · Swiss roll, direct matchingRMSE: 0.60 -> 0.33Improved
use shrinkage CMO estimation (S-CMP) instead of exact CMPCMP · Swiss roll, direct matchingRMSE: 0.33 -> 0.25Improved
use shrinkage CMO estimation (S-CMP) instead of exact CMPCMP · Swiss roll, indirect matchingRMSE: 0.80 -> 1.05Hurt
use CMP instead of BAGG-GPbag GP · Swiss roll, indirect matchingRMSE: 1.13 -> 0.80Improved
use VarCMP instead of VBAGGvariational bag GP · Swiss roll, indirect matchingRMSE: 1.46 -> 0.87Improved
use VarCMP instead of GPRGP regression on centroids · Swiss roll, indirect matchingRMSE: 1.04 -> 0.87Improved
move from direct to indirect (mediated) matchingall models · Swiss rollRMSE: 0.18 -> 0.87Hurt
use VarCMP instead of VarGPRvariational GP baseline · CMIP6 temperature downscalingRMSE: 8.02 -> 7.40Improved
use VarCMP instead of VBAGGvariational bag GP · CMIP6 temperature downscalingRMSE: 8.25 -> 7.40Improved
use VarCMP instead of VarGPRvariational GP baseline · CMIP6 temperature downscalingSSIM: 0.212 -> 0.212No clear effect
use VarCMP instead of VBAGGvariational bag GP · CMIP6 temperature downscalingSSIM: 0.182 -> 0.212Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy