Efficient and Parsimonious Agnostic Active Learning
Not on the map. Why?
Abstract (arXiv)
We develop a new active learning algorithm for the streaming setting satisfying three important properties: 1) It provably works for any classifier representation and classification problem including those with severe noise. 2) It is efficiently implementable with an ERM oracle. 3) It is more aggressive than all previous approaches satisfying 1 and 2. To do this we create an algorithm based on a newly defined optimization problem and analyze it. We also conduct the first experimental analysis of all efficient agnostic active learning algorithms, evaluating their strengths and weaknesses in different settings.
Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). First posted on arXiv 29 Jun 2015.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 3; 2022: 6; 2023: 5; 2024: 2; 2025: 1.
17 papers.
Sort:
- 2022Active Fairness Auditingcited by 27
- 2022Efficient Active Learning with Abstentioncited by 21
- 2023Streaming Active Learning with Deep Neural Networkscited by 20
- 2022Instance-optimal PAC Algorithms for Contextual Banditscited by 16
- 2021Improved Algorithms for Agnostic Pool-based Active Classificationcited by 15
- 2022Active Learning with Neural Networks: Insights from Nonparametric Statisticscited by 13
- 2023Improved Algorithm for Deep Active Learning under Imbalance via Optimal Separationcited by 8
- 2024AHA: Human-Assisted Out-of-Distribution Generalization and Detectioncited by 7
- 2021Selective Sampling for Online Best-arm Identificationcited by 6
- 2023Multi-task Representation Learning for Pure Exploration in Linear Banditscited by 6
- 2022Data-Efficient Learning via Minimizing Hyperspherical Energycited by 4
- 2022Improved Adaptive Algorithm for Scalable Active Learning with Weak Labelercited by 4
5 more
- 2021Corruption Robust Active Learningcited by 3
- 2024Learning from Snapshots of Discrete and Continuous Data Streamscited by 2
- 2023Efficient Active Learning Halfspaces with Tsybakov Noise: A Non-convex Optimization Approachcited by 1
- 2025Towards Fundamental Limits for Active Multi-distribution Learningcited by 1
- 2023Deep Active Learning with Structured Neural Depth Searchcited by 0
- 2025Towards Fundamental Limits for Active Multi-distribution Learning21 Jun 2025
- 2024Learning from Snapshots of Discrete and Continuous Data Streams8 Dec 2024
- 2024AHA: Human-Assisted Out-of-Distribution Generalization and Detection10 Oct 2024
- 2023Improved Algorithm for Deep Active Learning under Imbalance via Optimal Separation14 Dec 2023
- 2023Efficient Active Learning Halfspaces with Tsybakov Noise: A Non-convex Optimization Approach23 Oct 2023
- 2023Deep Active Learning with Structured Neural Depth Search5 Jun 2023
- 2023Streaming Active Learning with Deep Neural Networks5 Mar 2023
- 2023Multi-task Representation Learning for Pure Exploration in Linear Bandits9 Feb 2023
- 2022Improved Adaptive Algorithm for Scalable Active Learning with Weak Labeler4 Nov 2022
- 2022Active Learning with Neural Networks: Insights from Nonparametric Statistics15 Oct 2022
- 2022Instance-optimal PAC Algorithms for Contextual Bandits5 Jul 2022
- 2022Data-Efficient Learning via Minimizing Hyperspherical Energy30 Jun 2022
5 more
- 2022Active Fairness Auditing16 Jun 2022
- 2022Efficient Active Learning with Abstention31 Mar 2022
- 2021Selective Sampling for Online Best-arm Identification28 Oct 2021
- 2021Corruption Robust Active Learning21 Jun 2021
- 2021Improved Algorithms for Agnostic Pool-based Active Classification13 May 2021
- 2022Active Fairness Auditingcited by 27
- 2022Efficient Active Learning with Abstentioncited by 21
- 2023Streaming Active Learning with Deep Neural Networkscited by 20
- 2022Instance-optimal PAC Algorithms for Contextual Banditscited by 16
- 2021Improved Algorithms for Agnostic Pool-based Active Classificationcited by 15
- 2022Active Learning with Neural Networks: Insights from Nonparametric Statisticscited by 13
- 2023Improved Algorithm for Deep Active Learning under Imbalance via Optimal Separationcited by 8
- 2024AHA: Human-Assisted Out-of-Distribution Generalization and Detectioncited by 7
- 2021Selective Sampling for Online Best-arm Identificationcited by 6
- 2023Multi-task Representation Learning for Pure Exploration in Linear Banditscited by 6
- 2022Data-Efficient Learning via Minimizing Hyperspherical Energycited by 4
- 2022Improved Adaptive Algorithm for Scalable Active Learning with Weak Labelercited by 4
12 most cited of 17 All 17 (JSON)
- 2025Towards Fundamental Limits for Active Multi-distribution Learning21 Jun 2025
- 2024Learning from Snapshots of Discrete and Continuous Data Streams8 Dec 2024
- 2024AHA: Human-Assisted Out-of-Distribution Generalization and Detection10 Oct 2024
- 2023Improved Algorithm for Deep Active Learning under Imbalance via Optimal Separation14 Dec 2023
- 2023Efficient Active Learning Halfspaces with Tsybakov Noise: A Non-convex Optimization Approach23 Oct 2023
- 2023Deep Active Learning with Structured Neural Depth Search5 Jun 2023
- 2023Streaming Active Learning with Deep Neural Networks5 Mar 2023
- 2023Multi-task Representation Learning for Pure Exploration in Linear Bandits9 Feb 2023
- 2022Improved Adaptive Algorithm for Scalable Active Learning with Weak Labeler4 Nov 2022
- 2022Active Learning with Neural Networks: Insights from Nonparametric Statistics15 Oct 2022
- 2022Instance-optimal PAC Algorithms for Contextual Bandits5 Jul 2022
- 2022Data-Efficient Learning via Minimizing Hyperspherical Energy30 Jun 2022
12 newest of 17 All 17 (JSON)