mlsanityData to 7 Oct 2026

Convergence of Uncertainty Sampling for Active Learning

arXiv 2110.15784 ↗First posted 29 Oct 2021cs.LG math.OCcited by 19

Not on the map. Why?

Abstract (arXiv)

Uncertainty sampling in active learning is heavily used in practice to reduce the annotation cost. However, there has been no wide consensus on the function to be used for uncertainty estimation in binary classification tasks and convergence guarantees of the corresponding active learning algorithms are not well understood. The situation is even more challenging for multi-category classification. In this work, we propose an efficient uncertainty estimator for binary classification which we also extend to multiple classes, and provide a non-asymptotic rate of convergence for our uncertainty sampling-based active learning algorithm in both cases under no-noise conditions (i.e., linearly separable data). We also extend our analysis to the noisy case and provide theoretical guarantees for our algorithm under the influence of noise in the task of binary and multi-class classification.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Builds on 4 of its 34 references that are in the map. First posted on arXiv 29 Oct 2021.

Builds on

4 of 34 references.

References · 4

  1. 2018Fast and Faster Convergence of SGD for Over-Parameterized Models and an Accelerated Perceptroncited by 143
  2. 2017Active Learning Using Uncertainty Informationcited by 28
  3. 2018Uncertainty Sampling is Preconditioned Stochastic Gradient Descent on Zero-One Losscited by 10
  4. 2016Interactive algorithms: from pool to streamcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 5; 2023: 4; 2024: 6; 2025: 2; 2026: 2.

19 papers.

Sort:

By area:

  1. 2023A Survey on Uncertainty Quantification Methods for Deep Learningcited by 78
  2. 2024Active Evaluation Acquisition for Efficient LLM Benchmarkingcited by 33
  3. 2022Active Surrogate Estimators: An Active Learning Approach to Label-Efficient Model Evaluationcited by 26
  4. 2022A Lagrangian Duality Approach to Active Learningcited by 24
  5. 2022Is margin all you need? An extensive empirical study of active learning on tabular datacited by 10
  6. 2023ProbVLM: Probabilistic Adapter for Frozen Vision-Language Modelscited by 7
  7. 2024Querying Easily Flip-flopped Samples for Deep Active Learningcited by 7
  8. 2023Understanding Uncertainty Sampling via Equivalent Losscited by 5
  9. 2024User-Side Realizationcited by 3
  10. 2025A Cost-Effective LLM-based Approach to Identify Wildlife Trafficking in Online Marketplacescited by 3
  11. 2022MAViC: Multimodal Active Learning for Video Captioningcited by 1
  12. 2023On the Convergence of Loss and Uncertainty-based Active Learning Algorithmscited by 1
7 more
  1. 2022Active Learning from the Webcited by 0
  2. 2024Improve Cost Efficiency of Active Learning over Noisy Datasetcited by 0
  3. 2024ADs: Active Data-sharing for Data Quality Assurance in Advanced Manufacturing Systemscited by 0
  4. 2024PH-Dropout: Practical Epistemic Uncertainty Quantification for View Synthesiscited by 0
  5. 2025Active Learning Methods for Efficient Data Utilization and Model Performance Enhancementcited by 0
  6. 2026Nearly Optimal Active Preference Learning and Its Application to LLM Alignmentcited by 0
  7. 2026Balancing Uncertainty and Diversity of Samples: Leveraging Diversity of Least, High Confidence Samples for Effective Active Learningcited by 0