AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Log-concave sampling: Metropolis-Hastings algorithms are fast

Raaz Dwivedi, Yuansi Chen, Martin J. Wainwright, Bin Yu

JMLR 2019 · Learning theory and algorithms › Sample complexity · approach: Learning under log-concave distributions · 119 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 ULA with MALA (add accept-reject step)ULA · Gaussian, strongly log-concave (kappa=4, delta=0.2)error-dependence slope of mixing time: 2.23 -> 0.33Improved
replace ULA with MALA (add accept-reject step)ULA · Gaussian, weakly log-concave (lambda_max=1000, lambda_min=1)error-dependence slope of mixing time: 3.92 -> 1.56Improved
replace ULA with MALAULA · Gaussian, weakly log-concave (lambda_max=1000, lambda_min=1)dimension-dependence slope of mixing time: 2.78 -> 1.61Improved
replace MRW with MALAMRW · Gaussian, weakly log-concave (lambda_max=1000, lambda_min=1)dimension-dependence slope of mixing time: 2.73 -> 1.61Improved
replace ULA with MALA or MRWULA · Gaussian, strongly log-concave (kappa=4, delta=0.2)dimension-dependence slope of mixing time: 1.01 -> 0.84No clear effect
use MALA instead of ULAULA · 2D Gaussian mixturediscretized TV error vs iterationsImproved
shrink ULA step size via smaller delta (0.2 -> 0.1)ULA · 2D Gaussian mixtureconvergence rateHurt
enlarge ULA step size via larger delta (0.2 -> 1.0)ULA · 2D Gaussian mixtureasymptotic TV errorHurt
use MALA instead of ULA and MRWULA/MRW · 2D Gaussian mixturetrace-plot stabilization and autocorrelationImproved
add preconditioning with Sigma_X^{-1/2}ULA and MRW · Bayesian logistic regression (d=2, n=50)mean error of posterior sample meanImproved
use MALA instead of ULAULA · Bayesian logistic regression (d=2, n=50)mean error vs iterationsImproved
increase MALA step size from d^-0.5 to d^-0.2 (ablation)MALA · Gaussian and logistic regression posterioraverage acceptance probabilityHurt

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