A Regression Approach to Certain Information Transmission Problems
This work addresses information transmission optimization, potentially improving communication systems, but appears incremental as it applies regression concepts from machine learning to a known bottleneck.
The paper tackles the problem of optimizing channel output processing in information transmission by showing that the optimal function is the conditional expectation operator when the channel model is known, and proposes a data-driven algorithm for cases without model knowledge, validated through numerical experiments.
A general information transmission model, under independent and identically distributed Gaussian codebook and nearest neighbor decoding rule with processed channel output, is investigated using the performance metric of generalized mutual information. When the encoder and the decoder know the statistical channel model, it is found that the optimal channel output processing function is the conditional expectation operator, thus hinting a potential role of regression, a classical topic in machine learning, for this model. Without utilizing the statistical channel model, a problem formulation inspired by machine learning principles is established, with suitable performance metrics introduced. A data-driven inference algorithm is proposed to solve the problem, and the effectiveness of the algorithm is validated via numerical experiments. Extensions to more general information transmission models are also discussed.