Kernel observers: Systems-theoretic modeling and inference of spatiotemporally evolving processes

Hassan A. Kingravi, Harshal Maske, Girish Chowdhary

Research output: Contribution to journalConference article

Abstract

We consider the problem of estimating the latent state of a spatiotemporally evolving continuous function using very few sensor measurements. We show that layering a dynamical systems prior over temporal evolution of weights of a kernel model is a valid approach to spatiotemporal modeling, and that it does not require the design of complex nonstationary kernels. Furthermore, we show that such a differentially constrained predictive model can be utilized to determine sensing locations that guarantee that the hidden state of the phenomena can be recovered with very few measurements. We provide sufficient conditions on the number and spatial location of samples required to guarantee state recovery, and provide a lower bound on the minimum number of samples required to robustly infer the hidden states. Our approach outperforms existing methods in numerical experiments.

Original languageEnglish (US)
Pages (from-to)3997-4005
Number of pages9
JournalAdvances in Neural Information Processing Systems
StatePublished - Jan 1 2016
Event30th Annual Conference on Neural Information Processing Systems, NIPS 2016 - Barcelona, Spain
Duration: Dec 5 2016Dec 10 2016

Fingerprint

Dynamical systems
Recovery
Sensors
Experiments

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Cite this

Kernel observers : Systems-theoretic modeling and inference of spatiotemporally evolving processes. / Kingravi, Hassan A.; Maske, Harshal; Chowdhary, Girish.

In: Advances in Neural Information Processing Systems, 01.01.2016, p. 3997-4005.

Research output: Contribution to journalConference article

@article{43f9715049af42f7a00db0d9e4afbda1,
title = "Kernel observers: Systems-theoretic modeling and inference of spatiotemporally evolving processes",
abstract = "We consider the problem of estimating the latent state of a spatiotemporally evolving continuous function using very few sensor measurements. We show that layering a dynamical systems prior over temporal evolution of weights of a kernel model is a valid approach to spatiotemporal modeling, and that it does not require the design of complex nonstationary kernels. Furthermore, we show that such a differentially constrained predictive model can be utilized to determine sensing locations that guarantee that the hidden state of the phenomena can be recovered with very few measurements. We provide sufficient conditions on the number and spatial location of samples required to guarantee state recovery, and provide a lower bound on the minimum number of samples required to robustly infer the hidden states. Our approach outperforms existing methods in numerical experiments.",
author = "Kingravi, {Hassan A.} and Harshal Maske and Girish Chowdhary",
year = "2016",
month = "1",
day = "1",
language = "English (US)",
pages = "3997--4005",
journal = "Advances in Neural Information Processing Systems",
issn = "1049-5258",

}

TY - JOUR

T1 - Kernel observers

T2 - Systems-theoretic modeling and inference of spatiotemporally evolving processes

AU - Kingravi, Hassan A.

AU - Maske, Harshal

AU - Chowdhary, Girish

PY - 2016/1/1

Y1 - 2016/1/1

N2 - We consider the problem of estimating the latent state of a spatiotemporally evolving continuous function using very few sensor measurements. We show that layering a dynamical systems prior over temporal evolution of weights of a kernel model is a valid approach to spatiotemporal modeling, and that it does not require the design of complex nonstationary kernels. Furthermore, we show that such a differentially constrained predictive model can be utilized to determine sensing locations that guarantee that the hidden state of the phenomena can be recovered with very few measurements. We provide sufficient conditions on the number and spatial location of samples required to guarantee state recovery, and provide a lower bound on the minimum number of samples required to robustly infer the hidden states. Our approach outperforms existing methods in numerical experiments.

AB - We consider the problem of estimating the latent state of a spatiotemporally evolving continuous function using very few sensor measurements. We show that layering a dynamical systems prior over temporal evolution of weights of a kernel model is a valid approach to spatiotemporal modeling, and that it does not require the design of complex nonstationary kernels. Furthermore, we show that such a differentially constrained predictive model can be utilized to determine sensing locations that guarantee that the hidden state of the phenomena can be recovered with very few measurements. We provide sufficient conditions on the number and spatial location of samples required to guarantee state recovery, and provide a lower bound on the minimum number of samples required to robustly infer the hidden states. Our approach outperforms existing methods in numerical experiments.

UR - http://www.scopus.com/inward/record.url?scp=85019215676&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85019215676&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:85019215676

SP - 3997

EP - 4005

JO - Advances in Neural Information Processing Systems

JF - Advances in Neural Information Processing Systems

SN - 1049-5258

ER -