AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

On Power Laws in Deep Ensembles

Ekaterina Lobacheva, Nadezhda Chirkova, Maxim Kodryan, Dmitry P Vetrov

NeurIPS 2020 · Architectures and efficiency › RNNs and normalization · approach: Efficient network compression and training · 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
apply temperature before averaging instead of after averaging (ablation)deep ensemble calibration · CIFAR-10/100, VGG, WideResNetpower-law fit of (C)NLL vs ensemble sizeImproved
calibrate NLL with optimal temperature instead of tau=1 (ablation)single VGG on CIFAR-100 · network size sweepNLL vs network sizeImproved
replace a single large network with a memory split ensemble of medium networks of same total parametersVGG/WideResNet · CIFAR-100CNLLImproved
increase member network size when ensemblingWideResNet/VGG ensembles · CIFAR-100CNLLHurt
fit power law on ensembles of size 1-4 to predict larger ensemblesCNLL power law · CIFAR-100prediction RMSEImproved
increase temperature in non-calibrated NLL ensemble (ablation)NLL_n(tau) · VGG CIFAR-100ensembling gain parameter bHurt

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