atlas

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

Accelerating the diffusion-based ensemble sampling by non-reversible dynamics

ICML 2020 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Stochastic gradient MCMC · 4 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
add skew-symmetric non-reversible interaction (Skew-B/Skew-N/Skew-k) to parallel SGLDSGLD on Covertype BLR / LDA · LDA ICML holdout perplexitytest perplexity: SGLD 1034.86 vs Skew-B(0.01) 1024.33Helped
increase interaction strength alpha of skew-symmetric drift (ablation)Skew-N on Ornstein-Uhlenbeck process · OU energy distance / MMDconvergence vs discretization errorMixed
increase interaction strength alpha in Skew-N (ablation)Skew-N on Bayesian logistic regression · Covertype test accuracy / LLconvergence speed vs discretization errorMixed
add skew-symmetric interaction to SGLD on Kin8nm BNN regressionSGLD · Kin8nm BNN regressiontest RMSE: 6.92 to 6.86 (Skew-N)Helped
use skew-symmetric interaction on SVGD-style ensemble for LDA robustness to alpha (ablation)proposed skew-symmetric method on LDA · LDA holdout perplexitytest perplexityNo clear effect
add skew-symmetric interaction to SGLD on BNN classification (MNIST)SGLD · MNIST classificationaccuracyNo clear effect

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