Diameter-Based Active Learning
arXiv:1702.08553v227 citations
Originality Incremental advance
AI Analysis
This work addresses the challenge of efficient active learning for machine learning practitioners, though it appears incremental as it builds on existing bounds.
The paper tackled the problem of achieving the theoretical upper bound for active learning of general concept classes, and presented an efficient algorithm that empirically demonstrated good performance.
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.