On a quick skim it looks like that fails both “not equivalent to executing the model” and the float32 vs R problem.
float32
It’s a nice approach, but I’d also be surprised if it scales to maintain tight bounds on much larger networks.
On a quick skim it looks like that fails both “not equivalent to executing the model” and the
float32vs R problem.It’s a nice approach, but I’d also be surprised if it scales to maintain tight bounds on much larger networks.