AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Derivative-Informed Neural Operator Acceleration of Geometric MCMC for Infinite-Dimensional Bayesian Inverse Problems

Lianghao Cao, Thomas O'Leary-Roseberry, Omar Ghattas

JMLR 2025 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Importance sampling and quadrature · 10 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
train the neural operator with Jacobian (derivative-informed) loss instead of conventional input-output lossmMALA with neural operator surrogate · Diffusion-reaction and hyperelastic BIPseffective sample generation speed: 18--40 times fasterImproved
use DINO-driven geometric MCMC instead of prior-geometry pCNpCN · Diffusion-reaction and hyperelastic BIPseffective sample generation speed: 60--97 times fasterImproved
use DINO-driven geometric MCMC instead of full geometric MCMCmMALA · Diffusion-reaction and hyperelastic BIPseffective sample generation speed: 3--9 times fasterImproved
add derivative-informed trainingReduced basis neural operator · Diffusion-reaction and hyperelastic BIPstraining sample generation cost for equal Jacobian accuracy: 16--25 times lower costImproved
add derivative-informed trainingReduced basis neural operator · Nonlinear diffusion-reactiontraining sample cost to accelerate geometric MCMC: 166 times differenceImproved
use conventionally trained neural operator in mMALA (n_t=16000) instead of DINO (ablation)NO-mMALA · Diffusion-reaction coefficient inversionmean square jump (x1e-3): 11 -> 2.1Hurt
increase DINO training samples from 2000 to 16000 (ablation)DINO-mMALA · Diffusion-reaction coefficient inversionstep size (x1e-2): 12 -> 15Improved
add delayed acceptance to the conventional neural operator mMALA (ablation)NO-mMALA · Diffusion-reaction coefficient inversionmean square jump (x1e-3): 2.1 -> 1.1Hurt
use geometric proposal (mMALA) instead of prior-geometry pCNpCN · Diffusion-reaction coefficient inversionmean square jump (x1e-3): 1 -> 12Improved

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