AI Paper Atlas

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

SLANG: Fast Structured Covariance Approximations for Bayesian Deep Learning with Natural Gradient

Aaron Mishkin, Frederik Kunstner, Didrik Nielsen, Mark Schmidt, Mohammad Emtiyaz Khan

NeurIPS 2018 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Variational Bayesian deep learning · 24 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 a low-rank plus diagonal covariance approximation instead of a mean-field covarianceSLANG Bayesian logistic regression · Australian, Breast Cancer, a1a, USPS 3vs5ELBO: 0.614 -> 0.566; 0.122 -> 0.111; 0.384 -> 0.373; 0.268 -> 0.193Improved
Use SLANG instead of BBBBayesian neural networks · UCI regression datasetsTest RMSE: outperforms BBB on 7 out of 8 datasetsImproved
Use SLANG instead of Bayesian DropoutBayesian neural networks · UCI regression datasetsTest RMSEMixed
Increase the SLANG covariance rank (ablation)Bayesian logistic regression · Australian, Breast Cancer, a1a, USPS 3vs5ELBO: Australian: 0.574 -> 0.569; Breast Cancer: 0.112 -> 0.111; a1a: 0.377 -> 0.374; USPS 3vs5: 0.210 -> 0.198Improved
Increase the SLANG covariance rank (ablation)SLANG Bayesian neural network · MNISTTest Error: 2.00% -> 1.73%; L=8: 1.92%Mixed
Replace the SLANG precision-update projection with online eigendecomposition and moving-average factor updates (ablation)SLANG-OnlineEig · Australian, Breast Cancer, a1a, USPS 3vs5ELBO: Australian L=5: 0.569 -> 0.652; Breast Cancer L=5: 0.111 -> 0.123; a1a L=5: 0.374 -> 0.383Hurt
Increase SLANG-OnlineEig rank from L=2 to L=5 (ablation)SLANG-OnlineEig · AustralianELBO: 0.578 -> 0.652Hurt
Use SLANG rather than the mean-field methodBayesian neural networks · USPS 3vs5 and Breast Cancer convergence experimentsELBO convergence speedImproved

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