I consider the sequential implementation of a target information structure. I characterize the set of decision time distributions induced by all signal processes that satisfy a per-period learning capacity constraint. I find that all decision time distributions have the same expectation, and the maximal and minimal elements by mean-preserving spread order are deterministic distribution and exponential distribution. The result implies that when time preference is risk loving (e.g. standard or hyperbolic discounting), Poisson signal is optimal since it induces the most risky exponential decision time distribution. When time preference is risk neutral (e.g. constant delay cost), all signal processes are equally optimal.