Skip to Main content Skip to Navigation
Conference papers

Doubly Iterative Turbo Equalization: Optimization Through Deep Unfolding

Abstract : This paper analyzes some emerging techniques from the broad area of Bayesian learning for the design of iterative receivers for single-carrier transmissions using bit-interleaved coded-modulation (BICM) in wideband channels. In particular, approximate Bayesian inference methods, such as expectation propagation (EP), and iterative signal-recovery methods, such as approximate message passing (AMP) algorithms are evaluated as frequency domain equalizers (FDE). These algorithms show that decoding performance can be improved by going beyond the established turbo-detection principles, by iterating over inner detection loops before decoding. A comparative analysis is performed for the case of quasistatic wideband communications channels, showing that the EP-based approach is more advantageous. Moreover, recent advances in structured learning are revisited for the iterative EP-based receiver by unfolding the inner detection loop, and obtaining a deep detection network with learnable parameters. To this end, a novel, mutual-information dependent learning cost function is proposed, suited to turbo detectors, and through learning, the detection performance of the deep EP network is optimized.
Complete list of metadata

Cited literature [22 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02901598
Contributor : Open Archive Toulouse Archive Ouverte (oatao) <>
Submitted on : Friday, July 17, 2020 - 1:13:48 PM
Last modification on : Wednesday, June 9, 2021 - 10:00:28 AM
Long-term archiving on: : Tuesday, December 1, 2020 - 12:09:16 AM

File

sahin_26238.pdf
Files produced by the author(s)

Identifiers

Citation

Serdar Sahin, Charly Poulliat, Antonio Cipriano, Marie-Laure Boucheret. Doubly Iterative Turbo Equalization: Optimization Through Deep Unfolding. 30th IEEE International Conference on Personal, Indoor and Mobile Radio Communications (PIMRC 2019), Sep 2019, Istanbul, Turkey. pp.1-6, ⟨10.1109/PIMRC.2019.8904409⟩. ⟨hal-02901598⟩

Share

Metrics

Record views

29

Files downloads

104