A new method for parameter estimation in probabilistic models: Minimum probability flow

TL;DR

This paper introduces Minimum Probability Flow (MPF), a novel parameter estimation method for probabilistic models that improves convergence speed and accuracy, demonstrated on continuous models and Ising spin glasses.

Contribution

The paper presents MPF, a new general method for parameter estimation in probabilistic models, outperforming existing techniques in speed and accuracy.

Findings

MPF converges faster than traditional methods.

MPF achieves lower error in parameter recovery.

Effective in both continuous and discrete state space models.

Abstract

Fitting probabilistic models to data is often difficult, due to the general intractability of the partition function. We propose a new parameter fitting method, Minimum Probability Flow (MPF), which is applicable to any parametric model. We demonstrate parameter estimation using MPF in two cases: a continuous state space model, and an Ising spin glass. In the latter case it outperforms current techniques by at least an order of magnitude in convergence time with lower error in the recovered coupling parameters.