An updated look on the convergence and consistency of data-driven dynamical models

TL;DR

This paper extends convergence and consistency analysis to nonlinear probabilistic models for data-driven dynamical systems, including controlled systems, under stability assumptions, with applications to linear systems and Markov chains.

Contribution

It provides new theoretical convergence and consistency results for nonlinear probabilistic models in dynamical systems, broadening previous point prediction analyses.

Findings

Derived convergence and consistency conditions for nonlinear probabilistic models.

Applied theoretical results to linear system identification and finite-state Markov chains.

Established bias expressions under stability and regularity assumptions.

Abstract

Deep sequence models are receiving significant interest in current machine learning research. By representing probability distributions that are fit to data using maximum likelihood estimation, such models can model data on general observation spaces (both continuous and discrete-valued). Furthermore, they can be applied to a wide range of modelling problems, including modelling of dynamical systems which are subject to control. The problem of learning data-driven models of systems subject to control is well studied in the field of system identification. In particular, there exist theoretical convergence and consistency results which can be used to analyze model behaviour and guide model development. However, these results typically concern models which provide point predictions of continuous-valued variables. Motivated by this, we derive convergence and consistency results for a class of nonlinear probabilistic models defined on a general observation space. The results rely on stability and regularity assumptions, and can be used to derive consistency conditions and bias expressions for nonlinear probabilistic models of systems under control. We illustrate the results on examples from linear system identification and Markov chains on finite state spaces.