If you read the series, you'll see that what you call "rejection sampling" is in fact the first thing that was tried, and it was set aside for performance reasons. Yes you can try to improve the perf of this kind of system, but the goal was to build something that would run with much less overhead than that. And this was accomplished, and it seems to me that the end result runs faster than any optimized version of the system you are proposing. So I'd be careful with dishing out what reads to me here like middlebrow dismissal.