AI Paper Atlas

Research map / Optimization / Optimizers

Stochastic Gradient Geodesic MCMC Methods

Chang Liu, Jun Zhu, Yang Song

NeurIPS 2016 · Optimization › Optimizers · approach: Stochastic gradient MCMC · 18 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
use gSGNHT (adaptive thermostat) instead of SGGMCspherical admixture model posterior sampling · 20News-differentlog-perplexityImproved
use subsampled stochastic gradients (batch) instead of full-batch in SGGMC/gSGNHT (ablation)SGGMC and gSGNHT for SAM · 20News-differentlog-perplexityImproved
use SGGMC/gSGNHT sampler instead of GMC-based samplersspherical admixture model posterior sampling · 20News-differentlog-perplexityImproved
use subsampled stochastic gradients instead of full data in SAM inference (ablation)gSGNHT for SAM · 150K Wikipedialog-perplexityImproved
use SGGMC/gSGNHT instead of GMC-apprMH and GMC-bGibbsspherical admixture model posterior sampling · 150K Wikipedialog-perplexityImproved
set diffusion-noise covariance V(x) to zero (no gradient noise correction) in SGGMC/gSGNHT for SAMSGGMC and gSGNHT · SAM experimentslog-perplexityNo 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