AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Exponential ergodicity of mirror-Langevin diffusions

Sinho Chewi, Thibaut Le Gouic, Chen Lu, Tyler Maunu, Philippe Rigollet, Austin Stromme

NeurIPS 2020 · Optimization › Nonconvex and smooth optimization · approach: Langevin sampling for nonconvex problems

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 Langevin diffusion with Newton-Langevin algorithm (mirror map = potential)Newton-Langevin Algorithm vs ULA/TULA · Generalized Gaussian (gamma=3/4), d=100, Sigma=diag(1..100)squared mean error and relative scatter errorImproved
use a large step size h=0.7 for all samplers (ablation)Newton-Langevin Algorithm vs ULA and TULA · ill-conditioned Gaussian d=100sample quality (qualitative)Improved
reduce step size to 0.05 for all samplers (ablation)ULA and TULA · ill-conditioned Gaussian d=100sample quality (qualitative)Mixed
replace ULA/TULA with Newton-LangevinNewton-Langevin Algorithm · 2D Bayesian logistic regression posteriorsample quality (qualitative)Improved
decrease step size from 0.05 to 0.01 in logistic regression (ablation)ULA and TULA · Bayesian logistic regressionexploration of posterior (qualitative): 0.05 -> 0.01No clear effect
sample a thin rectangle via Newton-Langevin on a barrier-approximated target instead of projected LangevinNewton-Langevin vs PLA and MALA · uniform on [-0.01,0.01]x[-1,1]W2 distanceImproved
use larger step size for PLA (ablation)Projected Langevin Algorithm · thin rectangle uniform samplingsample distributionHurt

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