Persönlicher Status und Werkzeuge

Prof. Dr. Martin Kleinsteuber

Contact:

E-mail: kleinsteuber@tum.de
Phone: +49-89-289-23619
Room: Z944

Research Interests

  • Blind Signal Separation and Robust Dimensionality Reduction, in particular for image- and audiodata analysis.
  • Methods for Data Reconstruction, in particular Dictionary Learning, Compressive Sensing, and Matrix Completion algorithms.
  • Non-convex Optimization, in particular the development and analysis of optimization methods with smooth constraints.

Editorial Activities

Most relevant publications

See here for the full list of publications.

R. Gribonval, R. Jenatton, F. Bach, M. Kleinsteuber, and M. Seibert
Sample Complexity of Dictionary Learning and other Matrix Factorizations
IEEE Trans. on Information Theory, doi: 10.1109/TIT.2015.2424238, (2015).
Preprint: [arXiv] Citation: [bibTeX]

M. Kiechle, T. Habigt, S. Hawe, and M. Kleinsteuber
A Bimodal Co-Sparse Analysis Model for Image Processing
Int. Journal of Computer Vision, doi 10.1007/s11263-014-0786-5, (2014).
Preprint: [arXiv] Citation: [bibTeX] Code: [.zip]

M. Kleinsteuber and H. Shen
Uniqueness Analysis of Non-Unitary Matrix Joint Diagonalization
IEEE Trans. on Signal Processing 61(7) 1786-1796, (2013).
Preprint: [PDF], Citation: [BibTeX]

S. Hawe, M. Kleinsteuber, and K. Diepold
Analysis Operator Learning and Its Application to Image Reconstruction
IEEE Trans. on Image Processing 22(6) 2138-2150, (2013).
[Preprint] [Code] [Project Page] 
[BibTeX]

M. Kleinsteuber
A sort-Jacobi algorithm for semisimple Lie algebras
Linear Algebra Appl. 430(1) 155-173, (2009)
Citation: [bibTeX] Preprint: [PDF]
 

H. Shen, M. Kleinsteuber and K. Hüper
Local Convergence Analysis of FastICA and Related Algorithms
IEEE Transactions on Neural Networks 19(6) 1022-1032, (2008)
Citation: [bibTeX] Preprint: [PDF]