Method for adapting the regularization parameter of weak continuity

N. D. Sidiropoulos, J. S. Baras

Research output: Contribution to journalArticle

Abstract

We invoke a basic lemma from the theory of so-called penalty methods of nonlinear programming to come up with a simple yet highly efficient block-adaptive training procedure that selects a suitable Weak Continuity (WC) regularization parameter by matching the complexity (`prior') of the resulting solution to that of a desired response. The matching is achieved using a simple binary search technique that is guaranteed to converge in very few steps; as such, it avoids many of the potential pitfalls of other iterative methods.

Original languageEnglish (US)
Pages (from-to)1009-1013
Number of pages5
JournalConference Record of the Asilomar Conference on Signals, Systems and Computers
Volume2
StatePublished - Jan 1 1997

Fingerprint

Nonlinear programming
Iterative methods

Cite this

Method for adapting the regularization parameter of weak continuity. / Sidiropoulos, N. D.; Baras, J. S.

In: Conference Record of the Asilomar Conference on Signals, Systems and Computers, Vol. 2, 01.01.1997, p. 1009-1013.

Research output: Contribution to journalArticle

@article{f8af6a5023e247aba8cd6419c7fdd79b,
title = "Method for adapting the regularization parameter of weak continuity",
abstract = "We invoke a basic lemma from the theory of so-called penalty methods of nonlinear programming to come up with a simple yet highly efficient block-adaptive training procedure that selects a suitable Weak Continuity (WC) regularization parameter by matching the complexity (`prior') of the resulting solution to that of a desired response. The matching is achieved using a simple binary search technique that is guaranteed to converge in very few steps; as such, it avoids many of the potential pitfalls of other iterative methods.",
author = "Sidiropoulos, {N. D.} and Baras, {J. S.}",
year = "1997",
month = "1",
day = "1",
language = "English (US)",
volume = "2",
pages = "1009--1013",
journal = "Conference Record of the Asilomar Conference on Signals, Systems and Computers",
issn = "1058-6393",
publisher = "IEEE Computer Society",

}

TY - JOUR

T1 - Method for adapting the regularization parameter of weak continuity

AU - Sidiropoulos, N. D.

AU - Baras, J. S.

PY - 1997/1/1

Y1 - 1997/1/1

N2 - We invoke a basic lemma from the theory of so-called penalty methods of nonlinear programming to come up with a simple yet highly efficient block-adaptive training procedure that selects a suitable Weak Continuity (WC) regularization parameter by matching the complexity (`prior') of the resulting solution to that of a desired response. The matching is achieved using a simple binary search technique that is guaranteed to converge in very few steps; as such, it avoids many of the potential pitfalls of other iterative methods.

AB - We invoke a basic lemma from the theory of so-called penalty methods of nonlinear programming to come up with a simple yet highly efficient block-adaptive training procedure that selects a suitable Weak Continuity (WC) regularization parameter by matching the complexity (`prior') of the resulting solution to that of a desired response. The matching is achieved using a simple binary search technique that is guaranteed to converge in very few steps; as such, it avoids many of the potential pitfalls of other iterative methods.

UR - http://www.scopus.com/inward/record.url?scp=0030646366&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030646366&partnerID=8YFLogxK

M3 - Article

VL - 2

SP - 1009

EP - 1013

JO - Conference Record of the Asilomar Conference on Signals, Systems and Computers

JF - Conference Record of the Asilomar Conference on Signals, Systems and Computers

SN - 1058-6393

ER -