Supplementary material: Benchmarking Deep Inverse Models over time, and the Neural-Adjoint method

Although the performance over time is the main performance that we want to benchmark, as pointed out by [3] the posterior matching is another metric to measure how good the inverse models are. Below we show the posterior matching score using Maximum Mean Discrepancy (MMD) as a measurement of how close the inferred posterior density is comparing with the ground truth (rejection sampled) distribution. Note that for a real-life problem (D4: meta-material) with higher dimensionality, the rejection sampling becomes intractable. The 3 MMD kernel used was 0.05, 0.2 and 0.9. The code is also available on the repository.