AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Variance reduction for Random Coordinate Descent-Langevin Monte Carlo

ZHIYAN DING, Qin Li

NeurIPS 2020 · Optimization › Nonconvex and smooth optimization · approach: Stochastic variance reduction · 0 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
replace full gradient with vanilla random coordinate descent (one random partial derivative) in U-LMCU-LMC · Gaussian counter-example, d>2number of finite-difference evaluations to reach epsilon accuracyNo clear effect
add randomized coordinate averaging variance reduction (RCAD) to RCD for overdamped LMCO-LMC · log-concave sampling theory (Lipschitz hessian)number of partial derivative evaluations: O~(d^2/epsilon) -> O~(d^{3/2}/epsilon)Improved
add RCAD variance reduction to RCD for underdamped LMCU-LMC · log-concave sampling theorynumber of partial derivative evaluations: O~(d^{3/2}/epsilon) -> O~(max{d^{4/3}/epsilon^{2/3}, d^{1/2}/epsilon})Improved
add RCAD to RCD for overdamped LMC while dropping the Lipschitz hessian assumptionO-LMC · log-concave sampling theory without hessian Lipschitznumber of partial derivative evaluations: O~(d^2/epsilon^2) -> O~(max{d^{3/2}/epsilon, d/epsilon^2})Improved
add RCAD variance reduction to RCD-O-LMC (ablation)RCD-O-LMC · Example 1: N(0,I_d), d=1000, MSE of phi(x)=|x_1|^2error vs stepsizeImproved
add RCAD variance reduction to RCD-U-LMC (ablation)RCD-U-LMC · Example 2: bimodal Gaussian mixture, MSE of phi(x)=|x_1|^2error vs stepsizeImproved

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