Joint Constellation Shaping Using Gradient Descent Approach for MU-MIMO Broadcast Channel
This is an incremental improvement for wireless communication systems, offering a learning-based method to enhance data rates in multi-user scenarios.
The paper tackles the problem of optimizing joint constellations for multi-user MIMO broadcast channels to maximize the minimum mutual information under a sum-power constraint, achieving rates comparable to linear precoders without requiring superposition coding or successive interference cancellation.
We introduce a learning-based approach to optimize a joint constellation for a multi-user MIMO broadcast channel ($T$ Tx antennas, $K$ users, each with $R$ Rx antennas), with perfect channel knowledge. The aim of the optimizer (MAX-MIN) is to maximize the minimum mutual information between the transmitter and each receiver, under a sum-power constraint. The proposed optimization method do neither impose the transmitter to use superposition coding (SC) or any other linear precoding, nor to use successive interference cancellation (SIC) at the receiver. Instead, the approach designs a joint constellation, optimized such that its projection into the subspace of each receiver $k$, maximizes the minimum mutual information $I(W_k;Y_k)$ between each transmitted binary input $W_k$ and the output signal at the intended receiver $Y_k$. The rates obtained by our method are compared to those achieved with linear precoders.