Minimax and L1 Curve Fitting in Non-Gaussian MAP Estimation

Peter D. Scott

doi:10.1109/TAC.1975.1101080

Minimax and L1 Curve Fitting in Non-Gaussian MAP Estimation

Peter D. Scott

Department of Computer Science and Engineering

Research output: Contribution to journal › Article › peer-review

1 Scopus citations

Abstract

A class of non-Gaussian estimation problems is equivalent to minimax and L1curve fitting. The curve fit is shown to be algebraically dual to optimization of a positive semidefinite quadratic form with linear inequalities, which is solved by a fast quadratic program based on Graves’ simplex algorithm. An example compares the performance of this estimator with the (suboptimal) minimum Mean Squared error (MMSE) estimations generated by quadratic curve fitting.

Original language	English
Pages (from-to)	690-691
Number of pages	2
Journal	IEEE Transactions on Automatic Control
Volume	20
Issue number	5
DOIs	https://doi.org/10.1109/TAC.1975.1101080
State	Published - Oct 1975

Access to Document

10.1109/TAC.1975.1101080

Cite this

@article{02b5fa6655cb4f0886f3e9e4293cde61,

title = "Minimax and L1 Curve Fitting in Non-Gaussian MAP Estimation",

abstract = "A class of non-Gaussian estimation problems is equivalent to minimax and L1curve fitting. The curve fit is shown to be algebraically dual to optimization of a positive semidefinite quadratic form with linear inequalities, which is solved by a fast quadratic program based on Graves{\textquoteright} simplex algorithm. An example compares the performance of this estimator with the (suboptimal) minimum Mean Squared error (MMSE) estimations generated by quadratic curve fitting.",

author = "Scott, \{Peter D.\}",

year = "1975",

month = oct,

doi = "10.1109/TAC.1975.1101080",

language = "English",

volume = "20",

pages = "690--691",

journal = "IEEE Transactions on Automatic Control",

issn = "0018-9286",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "5",

}

TY - JOUR

T1 - Minimax and L1 Curve Fitting in Non-Gaussian MAP Estimation

AU - Scott, Peter D.

PY - 1975/10

Y1 - 1975/10

N2 - A class of non-Gaussian estimation problems is equivalent to minimax and L1curve fitting. The curve fit is shown to be algebraically dual to optimization of a positive semidefinite quadratic form with linear inequalities, which is solved by a fast quadratic program based on Graves’ simplex algorithm. An example compares the performance of this estimator with the (suboptimal) minimum Mean Squared error (MMSE) estimations generated by quadratic curve fitting.

AB - A class of non-Gaussian estimation problems is equivalent to minimax and L1curve fitting. The curve fit is shown to be algebraically dual to optimization of a positive semidefinite quadratic form with linear inequalities, which is solved by a fast quadratic program based on Graves’ simplex algorithm. An example compares the performance of this estimator with the (suboptimal) minimum Mean Squared error (MMSE) estimations generated by quadratic curve fitting.

UR - https://www.scopus.com/pages/publications/84939733997

U2 - 10.1109/TAC.1975.1101080

DO - 10.1109/TAC.1975.1101080

M3 - Article

AN - SCOPUS:84939733997

SN - 0018-9286

VL - 20

SP - 690

EP - 691

JO - IEEE Transactions on Automatic Control

JF - IEEE Transactions on Automatic Control

IS - 5

ER -

Minimax and L1 Curve Fitting in Non-Gaussian MAP Estimation

Abstract

Access to Document

Other files and links

Fingerprint

Cite this