New Machine Learning Techniques for Simulation-Based Inference: InferoStatic Nets, Kernel Score Estimation, and Kernel Likelihood Ratio Estimation
This work addresses simulation-based inference challenges for researchers in statistics and machine learning, presenting incremental improvements with new strategies and loss functions.
The authors tackled the problem of multiparameter inference when probability densities can be sampled but not computed directly, proposing InferoStatic Networks (ISN) with Kernel Score Estimation (KSE) and Kernel Likelihood Ratio Estimation (KLRE) to model score and likelihood ratio estimators, and illustrated these with toy examples and comparisons to existing methods.
We propose an intuitive, machine-learning approach to multiparameter inference, dubbed the InferoStatic Networks (ISN) method, to model the score and likelihood ratio estimators in cases when the probability density can be sampled but not computed directly. The ISN uses a backend neural network that models a scalar function called the inferostatic potential $\varphi$. In addition, we introduce new strategies, respectively called Kernel Score Estimation (KSE) and Kernel Likelihood Ratio Estimation (KLRE), to learn the score and the likelihood ratio functions from simulated data. We illustrate the new techniques with some toy examples and compare to existing approaches in the literature. We mention en passant some new loss functions that optimally incorporate latent information from simulations into the training procedure.