elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Incremental Reformulated Automatic Relevance Determination

Shutin, Dmitriy and Kulkarni, Sanjeev and Poor, H. Vincent (2012) Incremental Reformulated Automatic Relevance Determination. IEEE Transactions on Signal Processing, 4977 -4981. IEEE - Institute of Electrical and Electronics Engineers. DOI: 10.1109/TSP.2012.2200478 ISSN 1053-587X

[img] PDF - Registered users only
352kB

Abstract

In this work, the relationship between the incremental version of sparse Bayesian learning (SBL) with automatic relevance determination (ARD) - a fast marginal likelihood maximization (FMLM) algorithm - and a recently proposed reformulated ARD scheme is established. The FMLM algorithm is an incremental approach to SBL with ARD, where the corresponding objective function - the marginal likelihood - is optimized with respect to the parameters of a single component provided that the other parameters are fixed; the corresponding maximizer is computed in closed form, which enables a very efficient SBL realization. Wipf and Nagarajan have recently proposed a reformulated ARD (R-ARD) approach, which optimizes the marginal likelihood using auxiliary upper bounding functions. The resulting algorithm is then shown to correspond to a series of reweighted -constrained convex optimization problems. This correspondence establishes and analyzes the relationship between the FMLM and R-ARD schemes. Specifically, it is demonstrated that the FMLM algorithm realizes an incremental approach to the optimization of the R-ARD objective function. This relationship allows deriving the R-ARD pruning conditions similar to those used in the FMLM scheme to analytically detect components that are to be removed from the model, thus regulating the estimated signal sparsity and accelerating the algorithm convergence.

Item URL in elib:https://elib.dlr.de/95818/
Document Type:Article
Title:Incremental Reformulated Automatic Relevance Determination
Authors:
AuthorsInstitution or Email of AuthorsAuthors ORCID iD
Shutin, DmitriyDmitriy.Shutin (at) dlr.deUNSPECIFIED
Kulkarni, Sanjeevkulkarni (at) princeton.eduUNSPECIFIED
Poor, H. Vincentpoor (at) princeton.eduUNSPECIFIED
Date:September 2012
Journal or Publication Title:IEEE Transactions on Signal Processing
Refereed publication:Yes
Open Access:No
Gold Open Access:No
In SCOPUS:Yes
In ISI Web of Science:Yes
DOI :10.1109/TSP.2012.2200478
Page Range:4977 -4981
Publisher:IEEE - Institute of Electrical and Electronics Engineers
ISSN:1053-587X
Status:Published
Keywords:Automatic relevance determination, fast marginal likelihood maximization, sparse Bayesian learning.
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Aeronautics
HGF - Program Themes:air traffic management and operations
DLR - Research area:Aeronautics
DLR - Program:L AO - Air Traffic Management and Operation
DLR - Research theme (Project):L - Communication, Navigation and Surveillance
Location: Oberpfaffenhofen
Institutes and Institutions:Institute of Communication and Navigation
Deposited By: Shutin, Dmitriy
Deposited On:21 Apr 2015 10:18
Last Modified:06 Sep 2019 15:17

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.