Research map / Label-efficient and robust learning / Recognition and long-tail
Achieving Minimax Rates in Pool-Based Batch Active Learning
Claudio Gentile, Zhilei Wang, Tong Zhang
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 |
|---|---|---|---|
| Stage-wise greedy G-optimal design with pseudo-labeling (Algorithm 1) for linear models, versus standard batch/passive baselines | pool-based batch active learning, linear models · theoretical analysis, noisy linear model under low-noise condition | excess risk vs label complexity | Improved |
| Constant batch size B reduced to as small as T^(2/(α+2)) instead of unbounded batch size | constant-batch variant of Algorithm 1 · theoretical analysis, linear models | excess risk vs label complexity (minimax rate) | No clear effect |
| Number of re-training stages kept at most logarithmic in pool size, automatically adapting to noise level | Algorithm 1 · theoretical analysis, linear models | number of stages L | Improved |
| Logistic-model extension with regularized logistic regression estimators and exponentially shrinking margin regions | Algorithm 2 (logistic case) · theoretical analysis, generalized linear logistic model | excess risk bound dependence on input dimension d | Hurt |
Closest papers by meaning
- Fast Rates in Pool-Based Batch Active Learning (JMLR 2024 · similarity 0.97)
- Batch Active Learning at Scale (NeurIPS 2021 · similarity 0.91)
- Learning Generalizable Batch Active Learning Strategies via Deep Q-networks (Student Abstract) (AAAI 2023 · similarity 0.87)
- Neural Active Learning Beyond Bandits (ICLR 2024 · similarity 0.85)
- Active Classification with Few Queries under Misspecification (NeurIPS 2024 · similarity 0.85)
- Active Learning of General Halfspaces: Label Queries vs Membership Queries (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.
