Paper Info
Title
Active Learning with Oracle Epiphany.
Abstract
We present a theoretical analysis of active learning with more realistic interactions with human oracles. Previous empirical studies have shown oracles abstaining on difficult queries until accumulating enough information to make label decisions. We formalize this phenomenon with an "oracle epiphany model" and analyze active learning query complexity under such oracles for both the realizable and the agnostic cases. Our analysis shows that active learning is possible with oracle epiphany, but incurs an additional cost depending on when the epiphany happens. Our results suggest new, principled active learning approaches with realistic oracles.
Year
Venue
Field
2016
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 29 (NIPS 2016)
Active learning,Computer science,Epiphany,Oracle,Artificial intelligence,Phenomenon,Empirical research
DocType
Volume
ISSN
Conference
29
1049-5258
Citations 
PageRank 
References 
0
0.34
0
Authors
5
Name
Order
Citations
PageRank
Tzu-Kuo Huang138131.65
Lihong Li22390128.53
Ara Vartanian321.39
Saleema Amershi477545.16
Xiaojin Zhu53586222.74