AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Diverse Ensemble Evolution: Curriculum Data-Model Marriage

Tianyi Zhou, Shengjie Wang, Jeff A. Bilmes

NeurIPS 2018 · Architectures and efficiency › RNNs and normalization · approach: Dataset distillation and data-efficient training · 19 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 model-selecting-sample constraint and diversity terms (ablation)DivE2 · CIFAR10test accuracy (%): 90.11 -> 94.36Improved
add model-selecting-sample constraint and diversity terms (ablation)DivE2 · CIFAR100test accuracy (%): 71.01 -> 78.89Improved
train with DivE2 instead of Bagging (Top-k NN-LossPredict)ensemble training · CIFAR100test accuracy (%): 73.62 -> 78.89Improved
train with DivE2 instead of RandINIT (Top-k NN-LossPredict)ensemble training · STL10test accuracy (%): 77.28 -> 80.49Improved
train with DivE2 instead of RandINIT (Top-k NN-LossPredict)ensemble training · CIFAR10test accuracy (%): 93.69 -> 94.36Improved
train with DivE2 instead of RandINIT (All Average)ensemble training · Fashion-MNISTtest accuracy (%): 91.13 -> 86.16Hurt
train with DivE2 instead of baselines across aggregation methodsensemble training · four datasetstest accuracy (%): e.g. 75.71 -> 79.12 on CIFAR100 All AverageMixed
use DivE2 for ensemble training; single model accuracysingle models · four datasetstest accuracy (%)Hurt

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