Research map / Bandits and online learning / Online convex optimization and games
Budgeted Online Active Learning with Expert Advice and Episodic Priors
Kristen Goebel, William Solow, Paola Pesantez-Cabrera, Markus Keller, Alan Fern
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 prior episodic data via PSA or ETS instead of the classic secretary algorithm (ablation) | BOAL with HEDGE experts · WOFOSTGym Wheat GRLV, budget 2 | RMSE: 0.94 -> 0.78 | Improved |
| add prior episodic data via ETS instead of SA (ablation) | BOAL with HEDGE experts · Cold-hardiness (mean), budget 2 | RMSE: 1.52 -> 1.51 | Improved |
| use informed query selection (SA, PSA, ETS) instead of uniform querying (ablation) | BOAL with HEDGE experts · WOFOSTGym | RMSE: 2.37 -> 1.45 (Sorghum NAVAIL, budget 2, UNI vs PSA) | Improved |
| use secretary algorithm (SA) instead of uniform querying (ablation) | BOAL with HEDGE experts · WOFOSTGym | RMSE | Mixed |
| add labeled queries to the expert ensemble (ablation) | HEDGE expert weighting · WOFOSTGym | RMSE: 3.87 -> 2.39 (Maize NAVAIL, budget 2, Base vs ETS) | Improved |
| uniform querying with 2 queries versus no queries (ablation) | HEDGE expert weighting · Cold-hardiness (mean) | RMSE: 1.58 -> 1.64 | Hurt |
| add prior episodic data via ETS instead of PSA to the OnlineMax step (ablation) | OnlineMax · Cold-hardiness (mean), budget 2 | average selected SCORE: 1.62 -> 2.42 | Improved |
| replace expert set with weaker virtual experts (ablation) | BOAL methods · Cold-hardiness (mean), budget 2 | RMSE: 1.51 -> 1.58 (ETS) | No clear effect |
| increase query budget (ablation) | BOAL methods · Cold-hardiness (mean) | RMSE: 1.51 -> 1.49 (ETS, budget 2 -> 5) | No clear effect |
Closest papers by meaning
- Empowering and Assessing the Utility of Large Language Models in Crop Science (NeurIPS 2024 · similarity 0.83)
- Uncertainty Herding: One Active Learning Method for All Label Budgets (ICLR 2025 · similarity 0.83)
- Learning from Snapshots of Discrete and Continuous Data Streams (NeurIPS 2024 · similarity 0.82)
- Active Target Discovery under Uninformative Priors: The Power of Permanent and Transient Memory (NeurIPS 2025 · similarity 0.82)
- A Cross-Domain Benchmark for Active Learning (NeurIPS 2024 · similarity 0.82)
- Learning-Augmented Algorithms with Explicit Predictors (NeurIPS 2024 · similarity 0.82)
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.
