Unsupervised model-free representation learning

TL;DR

This paper introduces an unsupervised, model-free approach for learning representations of high-dimensional time-series data by maximizing a novel information criterion called time-series information, with implications for control tasks.

Contribution

It formulates a new unsupervised representation learning method for time-series data based on maximizing time-series information, including theoretical properties and control applications.

Findings

The representation function f maximizes time-series information.

Properties such as uniqueness and consistency are established.

Implications for optimal control are discussed.

Abstract

Numerous control and learning problems face the situation where sequences of high-dimensional highly dependent data are available but no or little feedback is provided to the learner, which makes any inference rather challenging. To address this challenge, we formulate the following problem. Given a series of observations $X_0,\dots,X_n$ coming from a large (high-dimensional) space $\mathcal X$, find a representation function $f$ mapping $\mathcal X$ to a finite space $\mathcal Y$ such that the series $f(X_0),\dots,f(X_n)$ preserves as much information as possible about the original time-series dependence in $X_0,\dots,X_n$. We show that, for stationary time series, the function $f$ can be selected as the one maximizing a certain information criterion that we call time-series information. Some properties of this functions are investigated, including its uniqueness and consistency of its empirical estimates. Implications for the problem of optimal control are presented.