Can Transformers Learn Optimal Filtering for Unknown Systems?

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Balim, Haldun, Du, Zhe, Oymak, Samet, Ozay, Necmiye
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929382341214208
author Balim, Haldun
Du, Zhe
Oymak, Samet
Ozay, Necmiye
author_facet Balim, Haldun
Du, Zhe
Oymak, Samet
Ozay, Necmiye
contents Transformer models have shown great success in natural language processing; however, their potential remains mostly unexplored for dynamical systems. In this work, we investigate the optimal output estimation problem using transformers, which generate output predictions using all the past ones. Particularly, we train the transformer using various distinct systems and then evaluate the performance on unseen systems with unknown dynamics. Empirically, the trained transformer adapts exceedingly well to different unseen systems and even matches the optimal performance given by the Kalman filter for linear systems. In more complex settings with non-i.i.d. noise, time-varying dynamics, and nonlinear dynamics like a quadrotor system with unknown parameters, transformers also demonstrate promising results. To support our experimental findings, we provide statistical guarantees that quantify the amount of training data required for the transformer to achieve a desired excess risk. Finally, we point out some limitations by identifying two classes of problems that lead to degraded performance, highlighting the need for caution when using transformers for control and estimation.
format Preprint
id arxiv_https___arxiv_org_abs_2308_08536
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Can Transformers Learn Optimal Filtering for Unknown Systems?
Balim, Haldun
Du, Zhe
Oymak, Samet
Ozay, Necmiye
Systems and Control
Artificial Intelligence
Machine Learning
Transformer models have shown great success in natural language processing; however, their potential remains mostly unexplored for dynamical systems. In this work, we investigate the optimal output estimation problem using transformers, which generate output predictions using all the past ones. Particularly, we train the transformer using various distinct systems and then evaluate the performance on unseen systems with unknown dynamics. Empirically, the trained transformer adapts exceedingly well to different unseen systems and even matches the optimal performance given by the Kalman filter for linear systems. In more complex settings with non-i.i.d. noise, time-varying dynamics, and nonlinear dynamics like a quadrotor system with unknown parameters, transformers also demonstrate promising results. To support our experimental findings, we provide statistical guarantees that quantify the amount of training data required for the transformer to achieve a desired excess risk. Finally, we point out some limitations by identifying two classes of problems that lead to degraded performance, highlighting the need for caution when using transformers for control and estimation.
title Can Transformers Learn Optimal Filtering for Unknown Systems?
topic Systems and Control
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2308.08536