Would running the method in this paper on EfficientNet count?
What if we instead used a weaker but still sound method (e.g. based on linear programs instead of semidefinite programs)?
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.
Would running the method in this paper on EfficientNet count?
What if we instead used a weaker but still sound method (e.g. based on linear programs instead of semidefinite programs)?
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.