AI Paper Atlas

Research map / Optimization / Optimizers

Quasi-Monte Carlo Quasi-Newton in Variational Bayes

Sifan Liu, Art B. Owen

JMLR 2021 · Optimization › Optimizers · 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
replace MC with RQMC (scrambled Sobol) sampling in AdaGradAdaGrad on Bayesian linear regression VB · Bayesian linear regression (N=300, d=100)log2 error vs nImproved
replace MC with RQMC in AdaGradAdaGrad · Bayesian logistic regression VB (N=30, d=100)ELBO vs wall clockImproved
use L-BFGS instead of AdaGradMC and RQMC sampling · Bayesian logistic regression VB (N=30, d=100)ELBO convergence speedImproved
replace MC with RQMC sampling in L-BFGS (8 gradient samples)L-BFGS · Crossed random effects VB (ng=8)ELBO fluctuationImproved
replace MC with RQMC sampling in BFGS (128 gradient samples)BFGS · Crossed random effects VB (ng=128)ELBOImproved
use BFGS instead of AdaGradMC and RQMC sampling · Crossed random effects VBtime to optimum / ELBOImproved
replace MC with RQMC in BFGSBFGS · VAE on MNISTELBOImproved
use BFGS instead of AdamVAE with MC and RQMC · VAE on MNISTconvergence speedImproved
go deeper into one RQMC sequence rather than fresh randomization each stepRQMC-SQN · VB examplesoptimization performanceNo clear effect

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