Data-Driven Estimation of Capacity Upper Bounds
Häger, Christian, Agrell, Erik
–arXiv.org Artificial Intelligence
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.
arXiv.org Artificial Intelligence
Sep-14-2022
- Country:
- Oceania > Australia
- North America > United States
- Illinois > Cook County
- Chicago (0.04)
- California
- San Diego County > San Diego (0.04)
- Los Angeles County
- Los Angeles (0.14)
- Long Beach (0.04)
- Illinois > Cook County
- Europe
- Sweden
- Vaestra Goetaland > Gothenburg (0.04)
- Stockholm > Stockholm (0.04)
- Spain > Catalonia
- Barcelona Province > Barcelona (0.04)
- Italy > Lazio
- Rome (0.04)
- France > Île-de-France
- Sweden
- Genre:
- Research Report (0.40)
- Technology: