New H ∞ bounds for the recursive least squares algorithm exploiting input structure

Koby Crammer; Alex Kulesza; Mark Dredze

doi:10.1109/ICASSP.2012.6288304

New H ^∞ bounds for the recursive least squares algorithm exploiting input structure

Koby Crammer, Alex Kulesza, Mark Dredze

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

The recursive least squares (RLS) algorithm is well known and has been widely used for many years. Most analyses of RLS have assumed statistical properties of the data or the noise process, but recent robust H ^∞ analyses have been used to bound the ratio of the performance of the algorithm to the total noise. In this paper, we provide an additive analysis bounding the difference between performance and noise. Our analysis provides additional convergence guarantees in general, and particular benefits for structured input data. We illustrate the analysis using human speech and white noise.

Original language	English (US)
Title of host publication	2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012 - Proceedings
Pages	2017-2020
Number of pages	4
DOIs	https://doi.org/10.1109/ICASSP.2012.6288304
State	Published - 2012
Externally published	Yes
Event	2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012 - Kyoto, Japan Duration: Mar 25 2012 → Mar 30 2012

Publication series

Name	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISSN (Print)	1520-6149

Conference

Conference	2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012
Country/Territory	Japan
City	Kyoto
Period	3/25/12 → 3/30/12

Keywords

Adaptive estimation
Adaptive signal processing
Machine learning

ASJC Scopus subject areas

Software
Signal Processing
Electrical and Electronic Engineering

Access to Document

10.1109/ICASSP.2012.6288304

Cite this

Crammer, K., Kulesza, A., & Dredze, M. (2012). New H ^∞ bounds for the recursive least squares algorithm exploiting input structure. In 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012 - Proceedings (pp. 2017-2020). Article 6288304 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). https://doi.org/10.1109/ICASSP.2012.6288304

New H ^∞ bounds for the recursive least squares algorithm exploiting input structure. / Crammer, Koby; Kulesza, Alex; Dredze, Mark.
2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012 - Proceedings. 2012. p. 2017-2020 6288304 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Crammer, K, Kulesza, A & Dredze, M 2012, New H ^∞ bounds for the recursive least squares algorithm exploiting input structure. in 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012 - Proceedings., 6288304, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, pp. 2017-2020, 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012, Kyoto, Japan, 3/25/12. https://doi.org/10.1109/ICASSP.2012.6288304

Crammer K, Kulesza A, Dredze M. New H ^∞ bounds for the recursive least squares algorithm exploiting input structure. In 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012 - Proceedings. 2012. p. 2017-2020. 6288304. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). doi: 10.1109/ICASSP.2012.6288304

@inproceedings{84581bfa7b4a4d4890a479d76f10beb2,

title = "New H ∞ bounds for the recursive least squares algorithm exploiting input structure",

abstract = "The recursive least squares (RLS) algorithm is well known and has been widely used for many years. Most analyses of RLS have assumed statistical properties of the data or the noise process, but recent robust H ∞ analyses have been used to bound the ratio of the performance of the algorithm to the total noise. In this paper, we provide an additive analysis bounding the difference between performance and noise. Our analysis provides additional convergence guarantees in general, and particular benefits for structured input data. We illustrate the analysis using human speech and white noise.",

keywords = "Adaptive estimation, Adaptive signal processing, Machine learning",

author = "Koby Crammer and Alex Kulesza and Mark Dredze",

year = "2012",

doi = "10.1109/ICASSP.2012.6288304",

language = "English (US)",

isbn = "9781467300469",

series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

pages = "2017--2020",

booktitle = "2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012 - Proceedings",

note = "2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012 ; Conference date: 25-03-2012 Through 30-03-2012",

}

TY - GEN

T1 - New H ∞ bounds for the recursive least squares algorithm exploiting input structure

AU - Crammer, Koby

AU - Kulesza, Alex

AU - Dredze, Mark

PY - 2012

Y1 - 2012

N2 - The recursive least squares (RLS) algorithm is well known and has been widely used for many years. Most analyses of RLS have assumed statistical properties of the data or the noise process, but recent robust H ∞ analyses have been used to bound the ratio of the performance of the algorithm to the total noise. In this paper, we provide an additive analysis bounding the difference between performance and noise. Our analysis provides additional convergence guarantees in general, and particular benefits for structured input data. We illustrate the analysis using human speech and white noise.

AB - The recursive least squares (RLS) algorithm is well known and has been widely used for many years. Most analyses of RLS have assumed statistical properties of the data or the noise process, but recent robust H ∞ analyses have been used to bound the ratio of the performance of the algorithm to the total noise. In this paper, we provide an additive analysis bounding the difference between performance and noise. Our analysis provides additional convergence guarantees in general, and particular benefits for structured input data. We illustrate the analysis using human speech and white noise.

KW - Adaptive estimation

KW - Adaptive signal processing

KW - Machine learning

UR - http://www.scopus.com/inward/record.url?scp=84867589410&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84867589410&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2012.6288304

DO - 10.1109/ICASSP.2012.6288304

M3 - Conference contribution

AN - SCOPUS:84867589410

SN - 9781467300469

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - 2017

EP - 2020

BT - 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012 - Proceedings

T2 - 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012

Y2 - 25 March 2012 through 30 March 2012

ER -