mlsanityData to 7 Oct 2026

Fast Rates in Pool-Based Batch Active Learning

arXiv 2202.05448 ↗First posted 11 Feb 2022cs.LG stat.MLcited by 15

Not on the map. Why?

Abstract (arXiv)

We consider a batch active learning scenario where the learner adaptively issues batches of points to a labeling oracle. Sampling labels in batches is highly desirable in practice due to the smaller number of interactive rounds with the labeling oracle (often human beings). However, batch active learning typically pays the price of a reduced adaptivity, leading to suboptimal results. In this paper we propose a solution which requires a careful trade off between the informativeness of the queried points and their diversity. We theoretically investigate batch active learning in the practically relevant scenario where the unlabeled pool of data is available beforehand (em pool-based active learning). We analyze a novel stage-wise greedy algorithm and show that, as a function of the label complexity, the excess risk of this algorithm matches the known minimax rates in standard statistical learning settings. Our results also exhibit a mild dependence on the batch size. These are the first theoretical results that employ careful trade offs between informativeness and diversity to rigorously quantify the statistical performance of batch active learning in the pool-based scenario.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 27 of its 66 references that are in the map. First posted on arXiv 11 Feb 2022.

Builds on

27 of 66 references.

References · 27

  1. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 602
  2. 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 428
  3. 2020GLISTER: Generalization based Data Subset Selection for Efficient and Robust Learningcited by 224
  4. 2021Batch Active Learning at Scalecited by 127
  5. 2020Improved Optimistic Algorithms for Logistic Banditscited by 117
  6. 2014Model-based Reinforcement Learning and the Eluder Dimensioncited by 116
  7. 2019Deep Active Learning: Unified and Principled Method for Query and Trainingcited by 92
  8. 2019Diverse mini-batch Active Learningcited by 88
  9. 2019Sequential Experimental Design for Transductive Linear Banditscited by 88
  10. 2020Task-Aware Variational Adversarial Active Learningcited by 84
  11. 2021SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarioscited by 83
  12. 2020Instance-Dependent Complexity of Contextual Bandits and Reinforcement Learning: A Disagreement-Based Perspectivecited by 78
15 more
  1. 2013Relative Loss Bounds for On-line Density Estimation with the Exponential Family of Distributionscited by 59
  2. 2021High-Dimensional Experimental Design and Kernel Banditscited by 55
  3. 2021Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvaturecited by 32
  4. 2021Data Shapley Valuation for Efficient Batch Active Learningcited by 27
  5. 2015Convergence Rates of Active Learning for Maximum Likelihood Estimationcited by 25
  6. 2019Adaptivity in Adaptive Submodularitycited by 22
  7. 2021Neural Active Learning with Performance Guaranteescited by 22
  8. 2021Improved Algorithms for Efficient Active Learning Halfspaces with Massart and Tsybakov noisecited by 18
  9. 2021Improved Algorithms for Agnostic Pool-based Active Classificationcited by 15
  10. 2020Chernoff Sampling for Active Testing and Extension to Active Regressioncited by 11
  11. 2017Diameter-Based Active Learningcited by 7
  12. 2021A Short Note on the Relationship of Information Gain and Eluder Dimensioncited by 7
  13. 2021Data Summarization via Bilevel Optimizationcited by 7
  14. 2016Near-optimal Bayesian Active Learning with Correlated and Noisy Testscited by 6
  15. 2021Selective Sampling for Online Best-arm Identificationcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 5; 2024: 4; 2025: 4; 2026: 2.

15 papers.

Sort:

By area:

  1. 2023Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-Constraintcited by 346
  2. 2023Active Prompting with Chain-of-Thought for Large Language Modelscited by 154
  3. 2023CoAnnotating: Uncertainty-Guided Work Allocation between Human and Large Language Models for Data Annotationcited by 93
  4. 2023Fairness-guided Few-shot Prompting for Large Language Modelscited by 53
  5. 2024Online Iterative Reinforcement Learning from Human Feedback with General Preference Modelcited by 52
  6. 2024Reinforcement Learning from Human Feedback with Active Queriescited by 39
  7. 2024Evolving Knowledge Distillation with Large Language Models and Active Learningcited by 12
  8. 2025Distributional Machine Unlearning via Selective Data Removalcited by 5
  9. 2023Primal Dual Continual Learning: Balancing Stability and Plasticity through Adaptive Memory Allocationcited by 4
  10. 2025System-Aware Unlearning Algorithms: Use Lesser, Forget Fastercited by 3
  11. 2025Daunce: Data Attribution through Uncertainty Estimationcited by 1
  12. 2025ActiveCQ: Active Estimation of Causal Quantitiescited by 1
3 more
  1. 2026Active Learning for Stochastic Contextual Linear Banditscited by 1
  2. 2024The Power of Adaptation: Boosting In-Context Learning through Adaptive Promptingcited by 0
  3. 2026Pool-based Active Learning as Noisy Lossy Compression: Characterizing Label Complexity via Finite Blocklength Analysiscited by 0