> We couldn't get it to work for two years," Li said, "and suddenly it started working. We got beautiful results that matched what we expected.
How many times have you gotten an algorithm to work, where later you realize you had an off by 1 error, or a double free somewhere in your code that you didn’t catch until you exposed your program to more situations?
I am curious about how they validated the ML approach. The advantage of simulation is the ability to uncover emergent phenomena that are difficult to predict and are not expected. It could be that they’re averaging a lot of common situations and they may miss novel outcomes.
The article only mentions a qualitative comparison but no incorporation of causal / physic based-modeling that I would imagine would be important in astronomy.
Easy enough for GAN to synthesize realistic, high-resolution images without any underlying model of reality / casuality.
It may look like the results of a high fidelity simulation, but how useful is that?