Research map / Learning theory and algorithms / Prediction and decision losses
IALE: Imitating Active Learner Ensembles
Christoffer Löffler, Christopher Mutschler
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 |
|---|---|---|---|
| Use IALE instead of Random Sampling | IALE · FMNIST | accuracy: 1-3% better | Improved |
| Use IALE instead of Random Sampling | IALE · KMNIST | accuracy: 7-9% ahead | Improved |
| Remove uncertainty experts (ablation) | IALE · KMNIST | accuracy | Hurt |
| Remove soft-max uncertainty experts (ablation) | IALE · KMNIST | accuracy | Hurt |
| Use fixed DAgger probability instead of exponential decay (ablation) | IALE policy training · transfer to another dataset | accuracy: by a small margin | Improved |
| Increase acquisition size while holding sub-pool size unchanged (ablation) | IALE · MNIST | accuracy | Hurt |
| Increase sub-pool size to 1,000 (ablation) | IALE · MNIST | accuracy | Improved |
| Increase sub-pool size beyond its suitable upper limit (ablation) | IALE · MNIST | accuracy | Hurt |
| Remove gradient representations from the state (ablation) | IALE · active learning datasets | accuracy | Hurt |
| Remove predicted-label representations from the state (ablation) | IALE · active learning datasets | accuracy | No clear effect |
| Use the full set of experts instead of leave-one-out expert sets (ablation) | IALE · active learning datasets | accuracy | Improved |
Closest papers by meaning
- Adversarial Imitation Learning via Boosting (ICLR 2024 · similarity 0.79)
- Instance-wise Supervision-level Optimization in Active Learning (CVPR 2025 · similarity 0.79)
- PREFER: Prompt Ensemble Learning via Feedback-Reflect-Refine (AAAI 2024 · similarity 0.79)
- Learning from Teaching Regularization: Generalizable Correlations Should be Easy to Imitate (NeurIPS 2024 · similarity 0.79)
- Agnostic Interactive Imitation Learning: New Theory and Practical Algorithms (ICML 2024 · similarity 0.79)
- Effortless Active Labeling for Long-Term Test-Time Adaptation (CVPR 2025 · similarity 0.79)
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.
