We study a persuasion problem in which a sender designs an information structure to induce a non-Bayesian receiver to take a particular action. The receiver, who is privately informed about his preferences, is a wishful thinker: he is systematically overoptimistic about the most favorable outcomes. We show that wishful thinking can lead to a qualitative shift in the structure of optimal persuasion compared to the Bayesian case, whenever the sender is uncertain about what the receiver perceives as the best-case outcome in his decision problem.