AI Paper Atlas

Research map / Optimization / Optimizers

Multilevel Monte Carlo Variational Inference

Masahiro Fujisawa, Issei Sato

JMLR 2021 · Optimization › Optimizers · approach: Stochastic gradient MCMC · 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
use MLMCVI instead of MCVI and QMCVI for gradient estimationMLMCVI · HLR, BLR, BNN benchmarkstraining ELBO convergence speedImproved
use MLMCVI instead of MCVI and QMCVIMLMCVI · HLR, BLR, BNN benchmarksempirical gradient varianceImproved
use MLMCVI instead of MCVI and QMCVIMLMCVI · HLR, BLR, BNN benchmarksempirical SNRImproved
use MLMCVI instead of baselines with a shared SGD and schedulerMLMCVI · Bayesian logistic regression, Fashion-MNISTtest log-likelihoodImproved
use MLMCVI with reduced training dataMLMCVI · Bayesian logistic regression, Fashion-MNISTtest log-likelihood: 20%Improved
vary scheduler hyperparameters (drop-rate r) and initial learning rate (ablation)MLMCVI · HLR, BLR, BNN benchmarksoptimization performanceMixed

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