Comparison of the posteriors for three dimension reduction techniques with respect to the reference posteriors computed by BXA. Left: PCA for which we retain 99.5% of the sample variance at each round. Center: spectral summary statistics computed over ten adjacent energy intervals. Right: our compact auto-encoder for which the spectra are reduced to a latent space of 64 dimensions. Over the five parameters of the model, the auto-encoder is clearly performing better than the two other reduction techniques.