AI Paper Atlas

Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes

Distributed Bayesian Learning with Stochastic Natural Gradient Expectation Propagation and the Posterior Server

Leonard Hasenclever, Stefan Webb, Thibaut Lienart, Sebastian Vollmer, Balaji Lakshminarayanan, Charles Blundell, Yee Whye Teh

JMLR 2017 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Variational Bayesian deep learning · 20 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
set power parameter beta=1/Nworkers (p-SNEP) instead of beta=1 (ablation)SNEP · MNIST 2-layer FCconvergence speed: eight workers reach a test error of 1.5% after about two epochs, much faster than beta=1.0Improved
add a second worker (vs one worker or Adam) (ablation)SNEP (beta=1) · MNIST 2-layer FCtest errorImproved
increase workers beyond two (ablation)SNEP (beta=1) · MNIST 2-layer FCtest errorHurt
increase workers with beta=1/Nworkers (ablation)p-SNEP · MNIST 2-layer FCtest error and convergenceImproved
communicate less often (Nsync up to once every 100 iterations) (ablation)SNEP · MNIST 2-layer FCtest errorNo clear effect
lower beta (ablation)SNEP · MNIST 2-layer FCconvergence speedImproved
use SNEP instead of SMS under Monte Carlo noisedistributed logistic regression (N=50000, d=50) · synthetic logistic regressionpredictive RMSEImproved
use p-SNEP instead of A-SGD and EASGD20x50 deep FC network · MNIST deep FC (8 and 16 workers)accuracy: an extra percent of accuracy after fifty epochsImproved
add noise to SGD methods (ablation)deep FC MNIST · MNIST deep FCrun varianceImproved
add L2 regularization (ablation)A-SGD and EASGD · MNIST deep FCaccuracyNo clear effect
use SNEP (beta=1) instead of p-SNEPCIFAR-10 CNN · CIFAR-10final test errorImproved

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