AI Paper Atlas

Research map / Optimization / Optimizers

Stochastic Gradient Descent as Approximate Bayesian Inference

Stephan Mandt, Matthew D. Hoffman, David M. Blei

JMLR 2017 · Optimization › Optimizers · approach: Stochastic gradient MCMC · 489 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
add full-rank preconditioning to constant SGD (ablation)constant SGD · WineKL divergence to posterior: 18.7 -> 0.7Improved
add full-rank preconditioning to constant SGD (ablation)constant SGD · SkinKL divergence to posterior: 0.471 -> 0.005Improved
add full-rank preconditioning to constant SGD (ablation)constant SGD · ProteinKL divergence to posterior: 1000.9 -> 1.8Improved
add diagonal preconditioning to constant SGD (ablation)constant SGD · Wine, Skin, ProteinKL divergence to posterior: 18.7 -> 14.0 (Wine), 0.471 -> 0.921 (Skin), 1000.9 -> 678.4 (Protein)Mixed
replace SGLD with constant SGD-f as approximate posterior samplerSGLD · Wine, Skin, ProteinKL divergence to posterior: 2.9 -> 0.7 (Wine), 0.905 -> 0.005 (Skin), 4.5 -> 1.8 (Protein)Improved
replace BBVI with constant SGD-f as posterior approximationBBVI · Wine, Skin, ProteinKL divergence to posterior: 44.7 -> 0.7 (Wine), 5.74 -> 0.005 (Skin), 478.1 -> 1.8 (Protein)Improved
use constant SGD-f instead of SGFS-fSGFS-f · Wine, Skin, ProteinKL divergence to posterior: 0.8 -> 0.7 (Wine), 0.005 -> 0.005 (Skin), 1.3 -> 1.8 (Protein)No clear effect
use IASG with constant learning rate instead of SGLD with decreasing rateSGLD · linear regression posterior variance estimationstandard error of marginal variance estimatesImproved
use IASG instead of NUTS and SGLD under random initializationNUTS and SGLD · linear regression posterior covariance, random initposterior covariance structure recoveryImproved
use constant SGD hyperparameter selection instead of BBVI for L2 strengthBBVI · MNIST and cover typevalidation lossNo 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