4th International Workshop on Total Least Squares and Errors-in-Variables Modeling
Arenberg castle, Leuven, Belgium, August 21-23, 2006
This interdisciplinary workshop is a continuation of 3 previous workshops which were held in Leuven, Belgium, August 1991, 1996, and 2001 and aims to bring together numerical analysts, statisticians, engineers, economists, chemists, etc. in order to discuss recent advances in Total Least Squares (TLS) techniques and errors-in-variables (EIV) modeling.
Presentations are solicited for technical sessions on the following and related topics:
- Concepts and Properties: structured and weighted TLS, other norms, misfit versus latency errors, nonlinear measurement error models, dynamic errors-in-variables, hypersurface fitting, statistical, numerical, robustness and optimization aspects
- Algorithms: real-time, adaptive, recursive, neural, iterative algorithms, based on SVD or related matrix/tensor decompositions, architectures, complexity, accuracy, regularization, convergence, lower rank approximations
- Applications: array signal and image processing, filtering, system identification, computer vision, document retrieval, spectral analysis, harmonic retrieval, direction finding, geology, chemistry, biomedicine
In particular, overview presentations describing recent advances on any of the above-mentioned topics are invited. Other topics related to total least squares, errors-in-variables modeling, and their applications are also welcome. Oral contributions are no longer accepted.
Special issues call for papers: Papers are invited for the special issues of
Computational Statistics & Data Analysis and
Signal Processing on the topic of the workshop. Papers submitted for the special issues need not be presented during the workshop.
Computational Statistics & Data Analysis CFP, Signal Processing CFP
- Chairpersons: Sabine Van Huffel and Ivan Markovsky, Katholieke Universiteit Leuven, BE
- Bart De Moor, Katholieke Universiteit Leuven, BE
- Yasuo Amemiya, IBM Research Center, USA
- Gene Golub, Stanford University, USA
- Bjorn Ottersten, Royal Institute of Technology, SE
- G.W. Stewart, University of Maryland, USA
- Rik Pintelon, Vrije Universiteit Brussel, BE
- Paul Van Dooren, Universite Catholique de Louvain, BE
- Nicola Mastronardi, CNR Bari, IT
- Richard Vaccaro, University of Rhode Island, USA
- Chi-Lun Cheng, Academia Sinica, Taiwan
- Alexander Kukush, University of Kiev, Ukraine
- Lieven De Lathauwer, CNRS-ETIS, FR
- Chris Paige, McGill University, CA
- Shalabh, Indian Institute of Technology Kanpur, IN
- Helmut Kuchenhoff, University of Munich, Germany
- Amir Beck (Technion - Israel Institute of Technology), The regularized total least squares problem: Theoretical properties and three globally convergent algorithms
- Ake Bjorck (Dept.\ of Mathematics, Linkoping University), A band Lanczos algorithm for least squares and total least squares problems
- Lieven De Lathauwer (Lab. ETIS, CNRS/ENSEA/UCP, Cergy-Pontoise, France), Principal component, independent component and parallel factor analysis
- Gene Golub (Dept. Computer Science, Stanford University, USA), Matrices and moments: perturbation for least squares
- Roberto Guidorzi, Roberto Diversi, and Umberto Soverini (Faculty of Engineering, University of Bologna, Italy), Some issues on errors-in-variables identification
- Kenichi Kanatani (Department of Computer Science, Okayama University, Japan), Hyperaccuracy for geometric fitting
- Nicola Mastronardi (CNR Bari, IT), Robust regression and l1 approximations for Toeplitz problems
- C. C. Paige (McGill University, Canada) and Z. Strakos (Academy of Sciences, Czech Republic), Bidiagonalization as a fundamental decomposition of data in linear approximation problems
- R. Pintelon and J. Schoukens (Vrije Universiteit Brussel, Belgium) Frequency domain maximum likelihood estimation of linear dynamic errors-in-variables models
- Jose Ramos (Purdue School of Engineering and Technology, USA), Applications of TLS and related methods in the environmental sciences
- Torsten Soderstrom (Department of Information Technology, Uppsala University, Sweden), Errors-in-variables methods in system identification
- Arie Yeredor (School of Electrical Engineering, Tel-Aviv University, Israel), On the role of constraints in system identification
- Chi-Lun Cheng (Institute of Statistical Science, Academia Sinica, Taiwan, R.O.C.), On the conditional score and corrected score estimation in nonlinear measurement error models
Ida Tassens
Dept. of Electrical Engineering,
ESAT-SCD (SISTA)
Katholieke Universiteit Leuven,
Kasteelpark Arenberg 10
B-3001 Leuven-Heverlee, Belgium
tel: 32/16/32.17.09, fax: 32/16/32.19.70
email: ida.tassens@esat.kuleuven.be
FWO SNR Advanced Numerical Methods for Mathematical Modelling (R. Cools - K.U.Leuven)