Diameter-Based Active Learning
Not on the map. Why?
Abstract (arXiv)
To date, the tightest upper and lower-bounds for the active learning of general concept classes have been in terms of a parameter of the learning problem called the splitting index. We provide, for the first time, an efficient algorithm that is able to realize this upper bound, and we empirically demonstrate its good performance.
Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 Feb 2017.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 2; 2022: 2; 2023: 0; 2024: 1; 2025: 1; 2026: 1.
7 papers.
- 2022Fast Rates in Pool-Based Batch Active Learningcited by 15
- 2024Boolean matrix logic programming for active learning of gene functions in genome-scale metabolic network modelscited by 2
- 2021Distribution Matching for Machine Teachingcited by 1
- 2022Targeted active learning for probabilistic modelscited by 1
- 2025Towards Fundamental Limits for Active Multi-distribution Learningcited by 1
- 2021Practical, Provably-Correct Interactive Learning in the Realizable Setting: The Power of True Believerscited by 0
- 2026Pool-based Active Learning as Noisy Lossy Compression: Characterizing Label Complexity via Finite Blocklength Analysiscited by 0
- 2026Pool-based Active Learning as Noisy Lossy Compression: Characterizing Label Complexity via Finite Blocklength Analysis5 Feb 2026
- 2025Towards Fundamental Limits for Active Multi-distribution Learning21 Jun 2025
- 2024Boolean matrix logic programming for active learning of gene functions in genome-scale metabolic network models10 May 2024
- 2022Targeted active learning for probabilistic models21 Oct 2022
- 2022Fast Rates in Pool-Based Batch Active Learning11 Feb 2022
- 2021Practical, Provably-Correct Interactive Learning in the Realizable Setting: The Power of True Believers9 Nov 2021
- 2021Distribution Matching for Machine Teaching6 May 2021