Active Learning of Classifiers with Label and Seed Queries

by   Marco Bressan, et al.

We study exact active learning of binary and multiclass classifiers with margin. Given an n-point set X ⊂ℝ^m, we want to learn any unknown classifier on X whose classes have finite strong convex hull margin, a new notion extending the SVM margin. In the standard active learning setting, where only label queries are allowed, learning a classifier with strong convex hull margin γ requires in the worst case Ω(1+1/γ)^(m-1)/2 queries. On the other hand, using the more powerful seed queries (a variant of equivalence queries), the target classifier could be learned in O(m log n) queries via Littlestone's Halving algorithm; however, Halving is computationally inefficient. In this work we show that, by carefully combining the two types of queries, a binary classifier can be learned in time poly(n+m) using only O(m^2 log n) label queries and O(m logm/γ) seed queries; the result extends to k-class classifiers at the price of a k!k^2 multiplicative overhead. Similar results hold when the input points have bounded bit complexity, or when only one class has strong convex hull margin against the rest. We complement the upper bounds by showing that in the worst case any algorithm needs Ω(k m log1/γ) seed and label queries to learn a k-class classifier with strong convex hull margin γ.


page 1

page 2

page 3

page 4


Active Learning from Weak and Strong Labelers

An active learner is given a hypothesis class, a large set of unlabeled ...

Active learning using region-based sampling

We present a general-purpose active learning scheme for data in metric s...

Agnostic Multi-Group Active Learning

Inspired by the problem of improving classification accuracy on rare or ...

Active Learning a Convex Body in Low Dimensions

Consider a set P ⊆R^d of n points, and a convex body C provided via a se...

The Power of Comparisons for Actively Learning Linear Classifiers

In the world of big data, large but costly to label datasets dominate ma...

Bounded Memory Active Learning through Enriched Queries

The explosive growth of easily-accessible unlabeled data has lead to gro...

Active Learning for Contextual Search with Binary Feedbacks

In this paper, we study the learning problem in contextual search, which...

Please sign up or login with your details

Forgot password? Click here to reset