Approximating the LLR Distribution for a Class of Soft-Output MIMO Detectors

Čirkić, Mirsad; Persson, Daniel; Larsson, Jan‐Åke; Larsson, Erik G.

doi:10.1109/tsp.2012.2217336

Cited by 4 publications

(2 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Only a few values are close to 0. In contrast, CMD provides meaningful soft information resembling a mixture of Gaussians as expected from literature [40] ranging from −30 to 30. These results strongly indicate that the difference of soft output quality originates from different underlying optimization strategies: As pointed out in Section III-B, unfolded CMD relies on minimization of KL divergence between IO a-posteriori and approximating pdf whereas the one-hot representation in DetNet is optimized w.r.t.…”

Section: F Soft Output (Coded System)mentioning

confidence: 72%

CMDNet: Learning a Probabilistic Relaxation of Discrete Variables for Soft Detection with Low Complexity

Beck,

Bockelmann,

Dekorsy

2021

Preprint

View full text Add to dashboard Cite

Following the great success of Machine Learning (ML), especially Deep Neural Networks (DNNs), in many research domains in 2010s, several learning-based approaches were proposed for detection in large inverse linear problems, e.g., massive MIMO systems. The main motivation behind is that the complexity of Maximum A-Posteriori (MAP) detection grows exponentially with system dimensions. Instead of using DNNs, essentially being a black-box in its most basic form, we take a slightly different approach and introduce a probabilistic Continuous relaxation of disCrete variables to MAP detection. Enabling close approximation and continuous optimization, we derive an iterative detection algorithm: ConCrete MAP Detection (CMD). Furthermore, by extending CMD to the idea of deep unfolding, we allow for (online) optimization of a small number of parameters to different working points while limiting complexity. In contrast to recent DNN-based approaches, we select the optimization criterion and output of CMD based on information theory and are thus able to learn approximate probabilities of the individual optimal detector. This is crucial for soft decoding in today's communication systems. Numerical simulation results in MIMO systems reveal CMD to feature a promising performance complexity trade-off compared to SotA. Notably, we demonstrate CMD's soft outputs to be reliable for decoders.

show abstract

Section: F Soft Output (Coded System)mentioning

confidence: 72%

CMDNet: Learning a Probabilistic Relaxation of Discrete Variables for Soft Detection with Low Complexity

Beck,

Bockelmann,

Dekorsy

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Only a few values are close to 0. In contrast, CMDNet provides meaningful soft information resembling a mixture of Gaussians as expected from literature [40] ranging from −30 to 30. These results strongly indicate that the difference of soft output quality originates from different underlying optimization strategies: As pointed out in Section III-B, CMDNet relies on minimization of KL divergence between IO a-posteriori and approximating softmax pmf whereas the one-hot representation in DetNet is optimized w.r.t.…”

Section: F Soft Output (Coded Mimo System)mentioning

confidence: 75%

CMDNet: Learning a Probabilistic Relaxation of Discrete Variables for Soft Detection With Low Complexity

Beck

Bockelmann

Dekorsy

2021

IEEE Trans. Commun.

View full text Add to dashboard Cite

Following the great success of Machine Learning (ML), especially Deep Neural Networks (DNNs), in many research domains in 2010s, several ML-based approaches were proposed for detection in large inverse linear problems, e.g., massive MIMO systems. The main motivation behind is that the complexity of Maximum A-Posteriori (MAP) detection grows exponentially with system dimensions. Instead of using DNNs, essentially being a black-box, we take a slightly different approach and introduce a probabilistic Continuous relaxation of disCrete variables to MAP detection. Enabling close approximation and continuous optimization, we derive an iterative detection algorithm: Concrete MAP Detection (CMD). Furthermore, extending CMD by the idea of deep unfolding into CMDNet, we allow for (online) optimization of a small number of parameters to different working points while limiting complexity. In contrast to recent DNN-based approaches, we select the optimization criterion and output of CMDNet based on information theory and are thus able to learn approximate probabilities of the individual optimal detector. This is crucial for soft decoding in today's communication systems. Numerical simulation results in MIMO systems reveal CMDNet to feature a promising accuracy complexity trade-off compared to State of the Art. Notably, we demonstrate CMDNet's soft outputs to be reliable for decoders.

show abstract

Probability Density Functions of L‐values

Szczeciński

Alvarado

2014

Bit‐Interleaved Coded Modulation

View full text Add to dashboard Cite

Approximating the LLR Distribution for a Class of Soft-Output MIMO Detectors

Cited by 4 publications

References 34 publications

CMDNet: Learning a Probabilistic Relaxation of Discrete Variables for Soft Detection with Low Complexity

CMDNet: Learning a Probabilistic Relaxation of Discrete Variables for Soft Detection with Low Complexity

CMDNet: Learning a Probabilistic Relaxation of Discrete Variables for Soft Detection With Low Complexity

Probability Density Functions of L‐values

Contact Info

Product

Resources

About