Disagreement-Based Active Learning in Online Settings

We study online active learning for classifying streaming instances within the framework of statistical learning theory. At each time, the learner either queries the label of the current instance or predicts the label based on past seen examples. The objective is to minimize the number of queries wh...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on signal processing Jg. 70; S. 1947 - 1958
Hauptverfasser: Huang, Boshuang, Salgia, Sudeep, Zhao, Qing
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York IEEE 2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Active learning
Algorithms
Classification
Complexity
Complexity theory
Distance learning
Errors
label complexity
Learning theory
Lower bounds
Machine learning
online learning
Optimization
Particle separators
Picture archiving and communication systems
Prediction algorithms
Queries
Real-time systems
regret
Signal processing algorithms
statistical learning theory
Tradeoffs
ISSN:1053-587X, 1941-0476
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:We study online active learning for classifying streaming instances within the framework of statistical learning theory. At each time, the learner either queries the label of the current instance or predicts the label based on past seen examples. The objective is to minimize the number of queries while constraining the number of prediction errors over a horizon of length <inline-formula><tex-math notation="LaTeX">T</tex-math></inline-formula>. We develop a disagreement-based online learning algorithm for a general hypothesis space and under the Tsybakov noise and establish its label complexity under a constraint of bounded regret in terms of classification errors. We further establish a matching (up to a poly-logarithmic factor) lower bound, demonstrating the order optimality of the proposed algorithm. We address the tradeoff between label complexity and regret and show that the algorithm can be modified to operate at a different point on the tradeoff curve.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1053-587X
1941-0476
DOI:10.1109/TSP.2022.3159388