Latent Representation and Simulation of Markov Processes via Time-Lagged Information Bottleneck

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Federici, Marco, Forré, Patrick, Tomioka, Ryota, Veeling, Bastiaan S.
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929225115631616
author Federici, Marco
Forré, Patrick
Tomioka, Ryota
Veeling, Bastiaan S.
author_facet Federici, Marco
Forré, Patrick
Tomioka, Ryota
Veeling, Bastiaan S.
contents Markov processes are widely used mathematical models for describing dynamic systems in various fields. However, accurately simulating large-scale systems at long time scales is computationally expensive due to the short time steps required for accurate integration. In this paper, we introduce an inference process that maps complex systems into a simplified representational space and models large jumps in time. To achieve this, we propose Time-lagged Information Bottleneck (T-IB), a principled objective rooted in information theory, which aims to capture relevant temporal features while discarding high-frequency information to simplify the simulation task and minimize the inference error. Our experiments demonstrate that T-IB learns information-optimal representations for accurately modeling the statistical properties and dynamics of the original process at a selected time lag, outperforming existing time-lagged dimensionality reduction methods.
format Preprint
id arxiv_https___arxiv_org_abs_2309_07200
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Latent Representation and Simulation of Markov Processes via Time-Lagged Information Bottleneck
Federici, Marco
Forré, Patrick
Tomioka, Ryota
Veeling, Bastiaan S.
Machine Learning
Artificial Intelligence
Information Theory
Markov processes are widely used mathematical models for describing dynamic systems in various fields. However, accurately simulating large-scale systems at long time scales is computationally expensive due to the short time steps required for accurate integration. In this paper, we introduce an inference process that maps complex systems into a simplified representational space and models large jumps in time. To achieve this, we propose Time-lagged Information Bottleneck (T-IB), a principled objective rooted in information theory, which aims to capture relevant temporal features while discarding high-frequency information to simplify the simulation task and minimize the inference error. Our experiments demonstrate that T-IB learns information-optimal representations for accurately modeling the statistical properties and dynamics of the original process at a selected time lag, outperforming existing time-lagged dimensionality reduction methods.
title Latent Representation and Simulation of Markov Processes via Time-Lagged Information Bottleneck
topic Machine Learning
Artificial Intelligence
Information Theory
url https://arxiv.org/abs/2309.07200