AI Paper Atlas

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

Efficient MCMC Sampling with Dimension-Free Convergence Rate using ADMM-type Splitting

Maxime Vono, Daniel Paulin, Arnaud Doucet

JMLR 2022 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Stochastic gradient MCMC

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 SGS instead of unadjusted Langevin in single splittingSGS · W1 complexity, strongly convex single splittinggradient evaluations: O*(kappa/eps^2) -> O*(kappa^{1/2}/eps)Improved
use SGS instead of ULA with multiple splittingSGS · TV complexity, multiple splittingevaluations: O*(kappa^2 d^3/eps^2) -> O*(kappa d^2/eps)Improved
use SGS bias instead of ULA bias at same step sizeSGS · Bias bound, TVTV bias: sqrt(2 M_1 d) rho -> 1/2 rho^2 M_1 dImproved
relax strong convexity to plain convexity (ablation)SGS multiple splitting · TV complexitymixing time: O*(M_1 d^2/eps^2)Hurt

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