Research map / Bandits and online learning / Online convex optimization and games
Selecting Near-Optimal Learners via Incremental Data Allocation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 DAUB data allocation instead of full training of all 41 learners | learner selection · HIGGS | training time (s): 49,905 -> 2,001 | Helped |
| use DAUB instead of full training | learner selection · PARITY | training time (s): 5,939 -> 397 | Helped |
| use DAUB across six benchmarks | learner selection · six real-world datasets | accuracy loss: avg loss 0.4%, avg speedup 16x | Helped |
| add training-accuracy upper bound f^T to DAUB (ablation) | DAUB · HIGGS | training time (s): 17,186 -> 2,001 | Helped |
| add training-accuracy upper bound f^T to DAUB (ablation) | DAUB · HIGGS | allocated samples: 590k -> 372k | Helped |
| add training-accuracy upper bound f^T to DAUB (ablation) | DAUB · PARITY | training time (s): 617 -> 397 | Helped |
| add training-accuracy upper bound f^T to DAUB (ablation) | DAUB · HIGGS | iterations: 105 -> 56 | Helped |
| add training-accuracy upper bound f^T to DAUB (ablation) | DAUB · PARITY | iterations: 26 -> 19 | Helped |
Closest papers by meaning
- Optimal Black-Box Reductions Between Optimization Objectives (NeurIPS 2016 · similarity 0.86)
- On discriminative learning of prediction uncertainty (ICML 2019 · similarity 0.86)
- Data-Efficient Learning via Clustering-Based Sensitivity Sampling: Foundation Models and Beyond (ICML 2024 · similarity 0.86)
- A Survey of Learning Criteria Going beyond the Usual Risk (Abstract Reprint) (AAAI 2024 · similarity 0.85)
- Uncertainty Herding: One Active Learning Method for All Label Budgets (ICLR 2025 · similarity 0.85)
- Diversified Batch Selection for Training Acceleration (ICML 2024 · similarity 0.85)
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.