Research map / Architectures and efficiency / RNNs and normalization
Diverse Ensemble Evolution: Curriculum Data-Model Marriage
Tianyi Zhou, Shengjie Wang, Jeff A. Bilmes
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add model-selecting-sample constraint and diversity terms (ablation) | DivE2 · CIFAR10 | test accuracy (%): 90.11 -> 94.36 | Improved |
| add model-selecting-sample constraint and diversity terms (ablation) | DivE2 · CIFAR100 | test accuracy (%): 71.01 -> 78.89 | Improved |
| train with DivE2 instead of Bagging (Top-k NN-LossPredict) | ensemble training · CIFAR100 | test accuracy (%): 73.62 -> 78.89 | Improved |
| train with DivE2 instead of RandINIT (Top-k NN-LossPredict) | ensemble training · STL10 | test accuracy (%): 77.28 -> 80.49 | Improved |
| train with DivE2 instead of RandINIT (Top-k NN-LossPredict) | ensemble training · CIFAR10 | test accuracy (%): 93.69 -> 94.36 | Improved |
| train with DivE2 instead of RandINIT (All Average) | ensemble training · Fashion-MNIST | test accuracy (%): 91.13 -> 86.16 | Hurt |
| train with DivE2 instead of baselines across aggregation methods | ensemble training · four datasets | test accuracy (%): e.g. 75.71 -> 79.12 on CIFAR100 All Average | Mixed |
| use DivE2 for ensemble training; single model accuracy | single models · four datasets | test accuracy (%) | Hurt |
Closest papers by meaning
- A Unified Theory of Diversity in Ensemble Learning (JMLR 2023 · similarity 0.88)
- DivBO: Diversity-aware CASH for Ensemble Learning (NeurIPS 2022 · similarity 0.86)
- Diverse Prototypical Ensembles Improve Robustness to Subpopulation Shift (ICML 2025 · similarity 0.86)
- Explore and Exploit the Diverse Knowledge in Model Zoo for Domain Generalization (ICML 2023 · similarity 0.86)
- Diversity By Design: Leveraging Distribution Matching for Offline Model-Based Optimization (ICML 2025 · similarity 0.85)
- Sharpness-diversity tradeoff: improving flat ensembles with SharpBalance (NeurIPS 2024 · similarity 0.84)
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.
