Paper Info
Title
Everything old is new again: A multi-view learning approach to learning using privileged information and distillation.
Abstract
We adopt a multi-view approach for analyzing two knowledge transfer settings---learning using privileged information (LUPI) and distillation---in a common framework. Under reasonable assumptions about the complexities of hypothesis spaces, and being optimistic about the expected loss achievable by the student (in distillation) and a transformed teacher predictor (in LUPI), we show that encouraging agreement between the teacher and the student leads to reduced search space. As a result, improved convergence rate can be obtained with regularized empirical risk minimization.
Year
Venue
DocType
2019
arXiv: Learning
Journal
Volume
Citations 
PageRank 
abs/1903.03694
0
0.34
References 
Authors
8
1
Name
Order
Citations
PageRank
Weiran Wang11149.99