Superimposed or time-multiplexed training: A performance comparison

We derive a performance comparison between the conventional time-multiplexing training based scheme and the most-recently proposed data-dependent superimposed training scheme, when using linear receivers. For both schemes, we derive an approximative closed-form expression for the Bit Error Rate (BER) and determine the optimal power allocation between pilot and data that minimizes the BER. Simulations are conducted to assess the accuracy of the provided expressions and to determine contexts for which it is more interesting to opt for the data-dependent superimposed training scheme.