mlsanityData to 7 Oct 2026

Beyond Disagreement-based Agnostic Active Learning

arXiv 1407.2657 ↗First posted 10 Jul 2014cs.LG stat.MLcited by 21

Not on the map. Why?

Abstract (arXiv)

We study agnostic active learning, where the goal is to learn a classifier in a pre-specified hypothesis class interactively with as few label queries as possible, while making no assumptions on the true function generating the labels. The main algorithms for this problem are emdisagreement-based active learning, which has a high label requirement, and emmargin-based active learning, which only applies to fairly restricted settings. A major challenge is to find an algorithm which achieves better label complexity, is consistent in an agnostic setting, and applies to general classification problems. In this paper, we provide such an algorithm. Our solution is based on two novel contributions -- a reduction from consistent active learning to confidence-rated prediction with guaranteed error, and a novel confidence-rated predictor.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Jul 2014.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 7; 2023: 2; 2024: 0; 2025: 2; 2026: 2.

21 papers.

Sort:

  1. 2021Machine Learning with a Reject Option: A surveycited by 107
  2. 2022Active Fairness Auditingcited by 27
  3. 2021Exponential Savings in Agnostic Active Learning through Abstentioncited by 23
  4. 2022Efficient Active Learning with Abstentioncited by 21
  5. 2021Improved Algorithms for Efficient Active Learning Halfspaces with Massart and Tsybakov noisecited by 18
  6. 2021Improved Algorithms for Agnostic Pool-based Active Classificationcited by 15
  7. 2021Active Learning in Bayesian Neural Networks with Balanced Entropy Learning Principlecited by 14
  8. 2023Agnostic Multi-Group Active Learningcited by 6
  9. 2022Data-Efficient Learning via Minimizing Hyperspherical Energycited by 4
  10. 2021Corruption Robust Active Learningcited by 3
  11. 2022Active Learning Polynomial Threshold Functionscited by 3
  12. 2022Contextual Active Model Selectioncited by 3
9 more
  1. 2025Towards Multimodal Active Learning: Efficient Learning with Limited Paired Datacited by 3
  2. 2021Error rate control for classification rules in multiclass mixture modelscited by 2
  3. 2022Black-box Generalization of Machine Teachingcited by 1
  4. 2022A Two-Stage Active Learning Algorithm for k-Nearest Neighborscited by 1
  5. 2023Efficient Active Learning Halfspaces with Tsybakov Noise: A Non-convex Optimization Approachcited by 1
  6. 2025Towards Fundamental Limits for Active Multi-distribution Learningcited by 1
  7. 2021Active Learning for Contextual Search with Binary Feedbackscited by 0
  8. 2026Pool-based Active Learning as Noisy Lossy Compression: Characterizing Label Complexity via Finite Blocklength Analysiscited by 0
  9. 2026Active Learning with Foundation Model Priors: Efficient Learning under Class Imbalancecited by 0