AI Paper Atlas

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

Gaussian Processes with Errors in Variables: Theory and Computation

Shuang Zhou, Debdeep Pati, Tianying Wang, Yun Yang, Raymond J. Carroll

JMLR 2023 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: PAC-Bayes and decoupled GP learning

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
model covariate measurement error (GPEV_a) instead of ignoring it (GP)GPEV_a · Synthetic EIV (n=100, delta^2=1)AMSE: 16$\cdot$81 -> 6$\cdot$31Improved
model measurement error (GPEV_a) instead of ignoring it (GP)GPEV_a · Synthetic EIV (n=500, delta^2=0.01)AMSE: 1$\cdot$80 -> 0$\cdot$13Improved
use GPEV_a instead of deconvolution kernel methodGPEV_a · Synthetic EIV (n=100, delta^2=1)AMSE: 20$\cdot$59 -> 6$\cdot$31Improved
use Dirichlet process mixture prior on covariate density instead of component-wise normal prior (ablation)GPEV_a · Synthetic EIV (n=100, delta^2=1)AMSE: 20$\cdot$98 -> 6$\cdot$31Improved
use DP mixture prior instead of component-wise normal prior (ablation)GPEV_a · Synthetic EIV (n=500, delta^2=1)AMSE: 20$\cdot$38 -> 3$\cdot$35Improved
use DP mixture prior instead of normal prior when error is tiny (ablation)GPEV_a · Synthetic EIV (n=500, delta^2=0.001)density recoveryNo clear effect
replace full GP (GPEV_f) with Fourier-basis approximation (GPEV_a) (ablation)GPEV_a · Synthetic EIV (n=100, delta^2=0.01)AMSE: 0$\cdot$55 -> 0$\cdot$58No clear effect
replace full GP with Fourier-basis approximation (ablation)GPEV_a · Synthetic EIV (n=500)time per MCMC iteration (s): 0.197 -> 0.025Improved
replace full GP with Fourier-basis approximation (ablation)GPEV_a · Synthetic EIV (n=500, delta^2=1)AMSE: 3$\cdot$94 -> 3$\cdot$35Mixed
use GPEV_a with fixed delta^2 vs unknown delta^2 with objective prior (ablation)GPEV_a · Real data (treatment group)MSE: 4.35 -> 4.54No clear effect
use GPEV_a instead of deconGPEV_a · Real data (treatment group)MSE: 8.23 -> 4.35Improved
use GPEV_a instead of deconGPEV_a · Real data (control group)MSE: 5.18 -> 3.87Improved

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