Time-series Random Process Complexity Ranking Using a Bound on Conditional Differential Entropy

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ayers, Jacob, Hahnloser, Richard, Ulrich, Julia, Krapp, Lothar Sebastian, Nitschke, Remo, Stoll, Sabine, Bickel, Balthasar, Furrer, Reinhard
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915571767967744
author Ayers, Jacob
Hahnloser, Richard
Ulrich, Julia
Krapp, Lothar Sebastian
Nitschke, Remo
Stoll, Sabine
Bickel, Balthasar
Furrer, Reinhard
author_facet Ayers, Jacob
Hahnloser, Richard
Ulrich, Julia
Krapp, Lothar Sebastian
Nitschke, Remo
Stoll, Sabine
Bickel, Balthasar
Furrer, Reinhard
contents Conditional differential entropy provides an intuitive measure for relatively ranking time-series complexity by quantifying uncertainty in future observations given past context. However, its direct computation for high-dimensional processes from unknown distributions is often intractable. This paper builds on the information theoretic prediction error bounds established by Fang et al. \cite{fang2019generic}, which demonstrate that the conditional differential entropy \textbf{$h(X_k \mid X_{k-1},...,X_{k-m})$} is upper bounded by a function of the determinant of the covariance matrix of next-step prediction errors for any next step prediction model. We add to this theoretical framework by further increasing this bound by leveraging Hadamard's inequality and the positive semi-definite property of covariance matrices. To see if these bounds can be used to rank the complexity of time series, we conducted two synthetic experiments: (1) controlled linear autoregressive processes with additive Gaussian noise, where we compare ordinary least squares prediction error entropy proxies to the true entropies of various additive noises, and (2) a complexity ranking task of bio-inspired synthetic audio data with unknown entropy, where neural network prediction errors are used to recover the known complexity ordering. This framework provides a computationally tractable method for time-series complexity ranking using prediction errors from next-step prediction models, that maintains a theoretical foundation in information theory.
format Preprint
id arxiv_https___arxiv_org_abs_2510_20551
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Time-series Random Process Complexity Ranking Using a Bound on Conditional Differential Entropy
Ayers, Jacob
Hahnloser, Richard
Ulrich, Julia
Krapp, Lothar Sebastian
Nitschke, Remo
Stoll, Sabine
Bickel, Balthasar
Furrer, Reinhard
Signal Processing
Information Theory
Audio and Speech Processing
Methodology
Machine Learning
Conditional differential entropy provides an intuitive measure for relatively ranking time-series complexity by quantifying uncertainty in future observations given past context. However, its direct computation for high-dimensional processes from unknown distributions is often intractable. This paper builds on the information theoretic prediction error bounds established by Fang et al. \cite{fang2019generic}, which demonstrate that the conditional differential entropy \textbf{$h(X_k \mid X_{k-1},...,X_{k-m})$} is upper bounded by a function of the determinant of the covariance matrix of next-step prediction errors for any next step prediction model. We add to this theoretical framework by further increasing this bound by leveraging Hadamard's inequality and the positive semi-definite property of covariance matrices. To see if these bounds can be used to rank the complexity of time series, we conducted two synthetic experiments: (1) controlled linear autoregressive processes with additive Gaussian noise, where we compare ordinary least squares prediction error entropy proxies to the true entropies of various additive noises, and (2) a complexity ranking task of bio-inspired synthetic audio data with unknown entropy, where neural network prediction errors are used to recover the known complexity ordering. This framework provides a computationally tractable method for time-series complexity ranking using prediction errors from next-step prediction models, that maintains a theoretical foundation in information theory.
title Time-series Random Process Complexity Ranking Using a Bound on Conditional Differential Entropy
topic Signal Processing
Information Theory
Audio and Speech Processing
Methodology
Machine Learning
url https://arxiv.org/abs/2510.20551