AI Paper Atlas

Research map / Probabilistic and scientific modeling / Differential equations and PDEs

Infinite-Fidelity Coregionalization for Physical Simulation

Shibo Li, Zheng Wang, Robert Kirby, Shandian Zhe

NeurIPS 2022 · Probabilistic and scientific modeling › Differential equations and PDEs · approach: Probabilistic inference for ODEs and SDEs · 0 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
model continuous fidelity with IFC-ODE^2 versus restricting to the highest training fidelity m=1 (extrapolate to 128x128 mesh)IFC-ODE^2 · PoissonnRMSE: 0.036 -> 0.018Improved
extrapolate IFC-ODE^2 beyond training fidelity to m=2.14IFC-ODE^2 · HeatnRMSE: 0.074 -> 0.061Improved
use GP prior over bases (IFC-GPODE) instead of latent ODE (IFC-ODE^2) for fidelities beyond training range m>1 (ablation)IFC · Poisson and Heat, extrapolation m>1nRMSEHurt
use GP prior (IFC-GPODE) instead of ODE^2 within training fidelity range, 0<=m<=1 (ablation)IFC · Poisson and Heat, interpolationnRMSEImproved
replace single-fidelity SF degeneration with infinite-fidelity IFC (ablation)IFC · Poisson, Heat, BurgersnRMSEImproved
IFC versus DRC, MFHoGP, DMF discrete-fidelity baselinesIFC-GPODE and IFC-ODE^2 · Poisson, Heat, Burgers, topology optimization, fluid dynamicsnRMSEImproved
increase latent output dimension K from 5 to 20 (ablation)IFC · Topology optimizationnRMSEImproved
use more hidden layers than two in NN components (ablation)IFC and DMF · PDE benchmarksnRMSENo clear effect
replace tanh with ReLU or LeakyReLU activation (ablation)IFC · PDE benchmarksnRMSEHurt
use ODE-based IFC instead of discrete-fidelity DMF/DRC for training costIFC-ODE^2 · Poisson training time, K=20seconds per epoch: 0.04 -> 7.84Hurt
use ODE-based IFC instead of DMF for training costIFC-ODE^2 · Fluid dynamics training time, K=20seconds per epoch: 0.10 -> 21.54Hurt

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