AI Paper Atlas

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

Deep Neural Networks with Dependent Weights: Gaussian Process Mixture Limit, Heavy Tails, Sparsity and Compressibility

Hoil Lee, Fadhel Ayed, Paul Jung, Juho Lee, Hongseok Yang, Francois Caron

JMLR 2023 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Infinite-width networks as Gaussian processes · 6 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 beta, horseshoe or generalised BFRY node variances instead of deterministic or inverse-gammainfinite-width FFNN · output dimension dependencecorrelation of squared outputs: width 2000: 0.001844 (deterministic), 0.004522 (inverse gamma) vs 0.297515 (beta), 0.253737 (horseshoe), 0.235673 (BFRY)Improved
increase width from 100 to 2000 for deterministic variance (ablation)FFNN with deterministic variance · output correlationcorrelation: 0.019994 -> 0.001844Improved
increase width from 100 to 2000 for beta variance (ablation)FFNN with beta variance · output correlationcorrelation: 0.320444 -> 0.297515No clear effect
use heavy-tailed variance (beta, horseshoe, BFRY) instead of light-tailedFFNN output distribution · width 2000, 50000 samplesoutput density tailImproved

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