I'm trying to replicate the results from a paper that uses the Manifold-PBO algorithm in a Monte Carlo simulation, but my implementation is producing significantly different convergence curves compared to the published results. The problem As shown in the images below, the left graph is from the original paper, and the right graph is my implementation using the code provided by the author:
I'm using MATLAB to run the exact same code sent by the author The Monte Carlo simulation parameters should be identical (same number of iterations, same network configuration) Running on MATLAB 2024 I've verified that all algorithm parameters match those described in the paper
Has anyone encountered similar issues when replicating Monte Carlo simulation results? What could be causing such a significant difference in convergence behavior and achieved rates? Any insights would be greatly appreciated. I'm particularly confused since I'm using the author's own implementation.
