TY - JOUR
T1 - Benchmarking Neural Capacity Estimation
T2 - Viability and Reliability
AU - Mirkarimi, Farhad
AU - Rini, Stefano
AU - Farsad, Nariman
N1 - Publisher Copyright:
© 1972-2012 IEEE.
PY - 2023/5/1
Y1 - 2023/5/1
N2 - Recently, several methods have been proposed for estimating the mutual information from sample data using deep neural networks. This approach is referred to as (). s differ from other approaches in the literature as they are data-driven estimators. As such, they have the potential to perform well on a large class of capacity problems. To test the performance across various s, it is desirable to establish a benchmark encompassing the different challenges of capacity estimation. This is the objective of this paper. We consider three scenarios for benchmarking: (i) the classic AWGN channel, (ii) channels continuous inputs- the optical intensity and peak-power constrained AWGN channel (iii) channels with a discrete output- i.e., the Poisson channel. We also consider the extension to the multi-terminal case with (iv) the AWGN and optical MAC models. We argue that benchmarking a certain across these four scenarios provides a substantive test of performance. We study the performance of mutual information neural estimator (MINE), smoothed mutual information lower-bound estimator (SMILE), and directed information neural estimator (DINE) and provide insights into the performance of other methods as well. To summarize our benchmarking results, MINE provides the most reliable performance.
AB - Recently, several methods have been proposed for estimating the mutual information from sample data using deep neural networks. This approach is referred to as (). s differ from other approaches in the literature as they are data-driven estimators. As such, they have the potential to perform well on a large class of capacity problems. To test the performance across various s, it is desirable to establish a benchmark encompassing the different challenges of capacity estimation. This is the objective of this paper. We consider three scenarios for benchmarking: (i) the classic AWGN channel, (ii) channels continuous inputs- the optical intensity and peak-power constrained AWGN channel (iii) channels with a discrete output- i.e., the Poisson channel. We also consider the extension to the multi-terminal case with (iv) the AWGN and optical MAC models. We argue that benchmarking a certain across these four scenarios provides a substantive test of performance. We study the performance of mutual information neural estimator (MINE), smoothed mutual information lower-bound estimator (SMILE), and directed information neural estimator (DINE) and provide insights into the performance of other methods as well. To summarize our benchmarking results, MINE provides the most reliable performance.
KW - AWGN channel
KW - Neural capacity estimators
KW - capacity
KW - optical intensity channel
KW - optimal input distribution
KW - peak power-constrained AWGN channel
KW - poisson channel
UR - http://www.scopus.com/inward/record.url?scp=85151546892&partnerID=8YFLogxK
U2 - 10.1109/TCOMM.2023.3255251
DO - 10.1109/TCOMM.2023.3255251
M3 - Article
AN - SCOPUS:85151546892
SN - 0090-6778
VL - 71
SP - 2654
EP - 2669
JO - IEEE Transactions on Communications
JF - IEEE Transactions on Communications
IS - 5
ER -