DCA for online prediction with expert advice

We investigate DC (Difference of Convex functions) programming and DCA (DC Algorithm) for a class of online learning techniques, namely prediction with expert advice, where the learner’s prediction is made based on the weighted average of experts’ predictions. The problem of predicting the experts’...

Full description

Saved in:
Bibliographic Details
Published in:Neural computing & applications Vol. 33; no. 15; pp. 9521 - 9544
Main Authors: Le Thi, Hoai An, Ho, Vinh Thanh
Format: Journal Article
Language:English
Published: London Springer London 01.08.2021
Springer Nature B.V
Springer Verlag
Subjects:
Algorithms
Artificial Intelligence
Computational Biology/Bioinformatics
Computational geometry
Computational Science and Engineering
Computer Science
Convex analysis
Convexity
Data Mining and Knowledge Discovery
Image Processing and Computer Vision
Machine learning
Optimization
Original Article
Predictions
Probability and Statistics in Computer Science
Online DC programming
Online learning
Online DCA
Prediction with expert advice
ISSN:0941-0643, 1433-3058
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We investigate DC (Difference of Convex functions) programming and DCA (DC Algorithm) for a class of online learning techniques, namely prediction with expert advice, where the learner’s prediction is made based on the weighted average of experts’ predictions. The problem of predicting the experts’ weights is formulated as a DC program for which an online version of DCA is investigated. The two so-called approximate/complete variants of online DCA based schemes are designed, and their regrets are proved to be logarithmic/sublinear. The four proposed algorithms for online prediction with expert advice are furthermore applied to online binary classification. Experimental results tested on various benchmark datasets showed their performance and their superiority over three standard online prediction with expert advice algorithms—the well-known weighted majority algorithm and two online convex optimization algorithms.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0941-0643
1433-3058
DOI:10.1007/s00521-021-05709-0