Loading...
Loading...

Go to the content (press return)

Squared-loss mutual information via high-dimension coherence matrix estimation

Author
De Cabrera, F.; Riba, J.
Type of activity
Presentation of work at congresses
Name of edition
2019 IEEE International Conference on Acoustics, Speech and Signal Processing
Date of publication
2019
Presentation's date
2019-05-12
Book of congress proceedings
2019 IEEE International Conference on Acoustics, Speech, and Signal Processing: proceedings: May 12-17, 2019: Brighton Conference Centre, Brighton, United Kingdom
First page
5142
Last page
5146
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
DOI
10.1109/ICASSP.2019.8682642
Project funding
Grup de processament del senyal i comunicacions
Wrestling with Interference in Communications and Information Processing (TEC2016-76409-C2-1-R)
Repository
http://hdl.handle.net/2117/185713 Open in new window
URL
https://ieeexplore.ieee.org/document/8682642 Open in new window
Abstract
Squared-loss mutual information (SMI) is a surro- gate of Shannon mutual information that is more advantageous for estimation. On the other hand, the coherence matrix of a pair of random vectors, a power-normalized version of the sample cross-covariance matrix, is a well-known second-order statistic found in the core of fundamental signal processing problems, such as canonical correlation analysis (CCA). This paper shows that SMI can be estimated from a pair of independent and identically distri...
Citation
De Cabrera, F.; Riba, J. Squared-loss mutual information via high-dimension coherence matrix estimation. A: IEEE International Conference on Acoustics, Speech, and Signal Processing. "2019 IEEE International Conference on Acoustics, Speech, and Signal Processing: proceedings: May 12-17, 2019: Brighton Conference Centre, Brighton, United Kingdom". Institute of Electrical and Electronics Engineers (IEEE), 2019, p. 5142-5146.
Keywords
Canonical correlation analysis, Characteristic function., Coherence matrix, Gaussian mixture models, Squared-Loss mutual Information
Group of research
SPCOM - Signal Processing and Communications Group

Participants