AI Paper Atlas

Research map / Optimization / Optimizers

Projected Stein Variational Gradient Descent

Peng Chen, Omar Ghattas

NeurIPS 2020 · Optimization › Optimizers · approach: Stein variational gradient descent · 27 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
project parameters to low-dimensional gradient-informed subspace (pSVGD instead of SVGD)SVGD · Bayesian logistic regression, Arcene (d=10,000)training time (s): 477 seconds -> 201 secondsImproved
project parameters to low-dimensional subspace (pSVGD instead of SVGD)SVGD · Bayesian logistic regression, Arceneprediction accuracyImproved
project parameters to low-dimensional subspace (pSVGD instead of SVGD)SVGD · elliptic PDE inverse problem, d from 289 to 16,641RMSE of pointwise sample varianceImproved
project parameters to low-dimensional subspace (pSVGD instead of SVGD)SVGD · conditional diffusion process, d=100posterior mean closeness to true parameterImproved
increase parameter dimension, number of samples, data pointspSVGD · elliptic PDE inverse problemeigenvalue decay / convergenceNo clear effect
add more processor cores K for same work (KN=1024 samples)pSVGD · elliptic PDE inverse problemCPU timeImproved

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