Publication: A deterministic analysis of an online convex mixture of experts algorithm
Loading...
Program
KU-Authors
Organization Authors
Co-Authors
Özkan, Hüseyin
Dönmez, Mehmet A.
Date
Language
Type
Embargo Status
N/A
Journal Title
Journal ISSN
Volume Title
Alternative Title
Abstract
We analyze an online learning algorithm that adaptively combines outputs of two constituent algorithms (or the experts) running in parallel to estimate an unknown desired signal. This online learning algorithm is shown to achieve and in some cases outperform the mean-square error (MSE) performance of the best constituent algorithm in the steady state. However, the MSE analysis of this algorithm in the literature uses approximations and relies on statistical models on the underlying signals. Hence, such an analysis may not be useful or valid for signals generated by various real-life systems that show high degrees of nonstationarity, limit cycles and that are even chaotic in many cases. In this brief, we produce results in an individual sequence manner. In particular, we relate the time-accumulated squared estimation error of this online algorithm at any time over any interval to the one of the optimal convex mixture of the constituent algorithms directly tuned to the underlying signal in a deterministic sense without any statistical assumptions. In this sense, our analysis provides the transient, steady-state, and tracking behavior of this algorithm in a strong sense without any approximations in the derivations or statistical assumptions on the underlying signals such that our results are guaranteed to hold. We illustrate the introduced results through examples.
Source
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Citation
item.page.haspartof
Source
IEEE Transactions on Neural Networks and Learning Systems
item.page.ispartofseries
item.page.edition
DOI
10.1109/TNNLS.2014.2346832
item.page.datauri
item.page.link
Rights
N/A
Copyrights Note
Rights and licensing
N/A
