We optimize delay diversity (DD) for the case when simple linear equalization (LE) is used at the receiver. We consider the general case of transmission over a correlated multiple-input multiple-output (MIMO) frequency-selective fading channel. The proposed optimization requires the knowledge of the statistical properties of the wireless channel at the transmitter, but channel state information is only required at the receiver side. Based on an approximation of the bit error rate for LE, we derive a stochastic gradient algorithm that allows us to optimize the DD transmit filters. Simulation results for the GSM/EDGE system show significant performance gains for the proposed optimized DD scheme over DD schemes reported previously (Gore, D. et al., Proc. IEEE Int. Conf. Commun., ICC, p.1949-53, 2002; Schober, R. et al., IEEE Trans. Wireless Commun., 2004), if LE is used at the receiver.