Active Learning with Simple Questions
Vasilis Kontonis, Mingchen Ma, Christos Tzamos

TL;DR
This paper explores a generalized active learning framework using region queries, quantifies the trade-off between query complexity and learning efficiency, and provides algorithms with optimal query bounds for various hypothesis classes.
Contribution
It introduces a VC dimension-based analysis of region query complexity in active learning, establishing upper and lower bounds, and develops efficient algorithms for specific hypothesis classes.
Findings
O(d log n) query complexity for learning with VC dimension d
Matching lower bounds showing necessity of VC dimension-based queries
Efficient algorithms for unions of intervals, high-dimensional boxes, and halfspaces
Abstract
We consider an active learning setting where a learner is presented with a pool S of n unlabeled examples belonging to a domain X and asks queries to find the underlying labeling that agrees with a target concept h^* \in H. In contrast to traditional active learning that queries a single example for its label, we study more general region queries that allow the learner to pick a subset of the domain T \subset X and a target label y and ask a labeler whether h^*(x) = y for every example in the set T \cap S. Such more powerful queries allow us to bypass the limitations of traditional active learning and use significantly fewer rounds of interactions to learn but can potentially lead to a significantly more complex query language. Our main contribution is quantifying the trade-off between the number of queries and the complexity of the query language used by the learner. We measure…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMachine Learning and Algorithms · Teaching and Learning Programming · Problem and Project Based Learning
MethodsSparse Evolutionary Training · Focus
