Data-Driven Estimation of Capacity Upper Bounds
Journal article, 2022

We consider the problem of estimating an upper bound on the capacity of a memoryless channel with unknown channel law and continuous output alphabet. A novel data-driven algorithm is proposed that exploits the dual representation of capacity where the maximization over the input distribution is replaced with a minimization over a reference distribution on the channel output. To efficiently compute the required divergence maximization between the conditional channel and the reference distribution, we use a modified mutual information neural estimator that takes the channel input as an additional parameter. We numerically evaluate our approach on different memoryless channels and show empirically that the estimated upper bounds closely converge either to the channel capacity or to best-known lower bounds.

Artificial neural networks

channel capacity

upper capacity bounds

Channel estimation

mutual information neural estimation

Training

duality

Autoencoders

divergence estimation

Estimation

dual capacity representation

neural networks

Upper bound

Neurons

Mutual information

Author

Christian Häger

Chalmers, Electrical Engineering, Communication, Antennas and Optical Networks

Erik Agrell

Chalmers, Electrical Engineering, Communication, Antennas and Optical Networks

IEEE Communications Letters

1089-7798 (ISSN) 15582558 (eISSN)

Vol. 26

Physics-Based Deep Learning for Optical Data Transmission and Distributed Sensing

Swedish Research Council (VR) (2020-04718), 2021-01-01 -- 2024-12-31.

Communications over bursty optical channels

Swedish Research Council (VR) (2021-03709), 2022-01-01 -- 2025-12-31.

Unlocking the Full-dimensional Fiber Capacity

Knut and Alice Wallenberg Foundation (KAW 2018.0090), 2019-07-01 -- 2024-06-30.

Areas of Advance

Information and Communication Technology

Subject Categories

Telecommunications

Communication Systems

Signal Processing

Infrastructure

C3SE (Chalmers Centre for Computational Science and Engineering)

DOI

10.1109/LCOMM.2022.3207385

More information

Latest update

7/17/2024