Stability Via Adversarial Training of Neural Network Stochastic Control of Mean-Field Type

Julian Barreiro-Gomez; Salah Eddine Choutri; Boualem Djehiche

doi:10.1109/CDC51059.2022.9993216

Stability Via Adversarial Training of Neural Network Stochastic Control of Mean-Field Type

Julian Barreiro-Gomez, Salah Eddine Choutri, Boualem Djehiche

Mathematics

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

In this paper, we present an approach to neural network mean-field-type control and its stochastic stability analysis by means of adversarial inputs (aka adversarial attacks). This is a class of data-driven mean-field-type control where the distribution of the variables such as the system states and control inputs are incorporated into the problem. Besides, we present a methodology to validate the feasibility of the approximations of the solutions via neural networks and evaluate their stability. Moreover, we enhance the stability by enlarging the training set with adversarial inputs to obtain a more robust neural network. Finally, a worked-out example based on the linear-quadratic mean-field type control problem (LQ-MTC) is presented to illustrate our methodology.

Original language	English (US)
Title of host publication	2022 IEEE 61st Conference on Decision and Control, CDC 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	7547-7552
Number of pages	6
ISBN (Electronic)	9781665467612
DOIs	https://doi.org/10.1109/CDC51059.2022.9993216
State	Published - 2022
Event	61st IEEE Conference on Decision and Control, CDC 2022 - Cancun, Mexico Duration: Dec 6 2022 → Dec 9 2022

Publication series

Name	Proceedings of the IEEE Conference on Decision and Control
Volume	2022-December
ISSN (Print)	0743-1546
ISSN (Electronic)	2576-2370

Conference

Conference	61st IEEE Conference on Decision and Control, CDC 2022
Country/Territory	Mexico
City	Cancun
Period	12/6/22 → 12/9/22

Keywords

adversarial training
data-driven control
Neural networks
robustness
stability
supervised machine learning

ASJC Scopus subject areas

Control and Systems Engineering
Modeling and Simulation
Control and Optimization

Access to Document

10.1109/CDC51059.2022.9993216

Cite this

Barreiro-Gomez, J., Choutri, S. E., & Djehiche, B. (2022). Stability Via Adversarial Training of Neural Network Stochastic Control of Mean-Field Type. In 2022 IEEE 61st Conference on Decision and Control, CDC 2022 (pp. 7547-7552). (Proceedings of the IEEE Conference on Decision and Control; Vol. 2022-December). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CDC51059.2022.9993216

Stability Via Adversarial Training of Neural Network Stochastic Control of Mean-Field Type. / Barreiro-Gomez, Julian; Choutri, Salah Eddine; Djehiche, Boualem.
2022 IEEE 61st Conference on Decision and Control, CDC 2022. Institute of Electrical and Electronics Engineers Inc., 2022. p. 7547-7552 (Proceedings of the IEEE Conference on Decision and Control; Vol. 2022-December).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Barreiro-Gomez, J, Choutri, SE & Djehiche, B 2022, Stability Via Adversarial Training of Neural Network Stochastic Control of Mean-Field Type. in 2022 IEEE 61st Conference on Decision and Control, CDC 2022. Proceedings of the IEEE Conference on Decision and Control, vol. 2022-December, Institute of Electrical and Electronics Engineers Inc., pp. 7547-7552, 61st IEEE Conference on Decision and Control, CDC 2022, Cancun, Mexico, 12/6/22. https://doi.org/10.1109/CDC51059.2022.9993216

@inproceedings{c9e0b343a8f4480598cebeece462e681,

title = "Stability Via Adversarial Training of Neural Network Stochastic Control of Mean-Field Type",

abstract = "In this paper, we present an approach to neural network mean-field-type control and its stochastic stability analysis by means of adversarial inputs (aka adversarial attacks). This is a class of data-driven mean-field-type control where the distribution of the variables such as the system states and control inputs are incorporated into the problem. Besides, we present a methodology to validate the feasibility of the approximations of the solutions via neural networks and evaluate their stability. Moreover, we enhance the stability by enlarging the training set with adversarial inputs to obtain a more robust neural network. Finally, a worked-out example based on the linear-quadratic mean-field type control problem (LQ-MTC) is presented to illustrate our methodology.",

keywords = "adversarial training, data-driven control, Neural networks, robustness, stability, supervised machine learning",

author = "Julian Barreiro-Gomez and Choutri, {Salah Eddine} and Boualem Djehiche",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 61st IEEE Conference on Decision and Control, CDC 2022 ; Conference date: 06-12-2022 Through 09-12-2022",

year = "2022",

doi = "10.1109/CDC51059.2022.9993216",

language = "English (US)",

series = "Proceedings of the IEEE Conference on Decision and Control",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "7547--7552",

booktitle = "2022 IEEE 61st Conference on Decision and Control, CDC 2022",

}

TY - GEN

T1 - Stability Via Adversarial Training of Neural Network Stochastic Control of Mean-Field Type

AU - Barreiro-Gomez, Julian

AU - Choutri, Salah Eddine

AU - Djehiche, Boualem

PY - 2022

Y1 - 2022

N2 - In this paper, we present an approach to neural network mean-field-type control and its stochastic stability analysis by means of adversarial inputs (aka adversarial attacks). This is a class of data-driven mean-field-type control where the distribution of the variables such as the system states and control inputs are incorporated into the problem. Besides, we present a methodology to validate the feasibility of the approximations of the solutions via neural networks and evaluate their stability. Moreover, we enhance the stability by enlarging the training set with adversarial inputs to obtain a more robust neural network. Finally, a worked-out example based on the linear-quadratic mean-field type control problem (LQ-MTC) is presented to illustrate our methodology.

AB - In this paper, we present an approach to neural network mean-field-type control and its stochastic stability analysis by means of adversarial inputs (aka adversarial attacks). This is a class of data-driven mean-field-type control where the distribution of the variables such as the system states and control inputs are incorporated into the problem. Besides, we present a methodology to validate the feasibility of the approximations of the solutions via neural networks and evaluate their stability. Moreover, we enhance the stability by enlarging the training set with adversarial inputs to obtain a more robust neural network. Finally, a worked-out example based on the linear-quadratic mean-field type control problem (LQ-MTC) is presented to illustrate our methodology.

KW - adversarial training

KW - data-driven control

KW - Neural networks

KW - robustness

KW - stability

KW - supervised machine learning

UR - http://www.scopus.com/inward/record.url?scp=85146987197&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85146987197&partnerID=8YFLogxK

U2 - 10.1109/CDC51059.2022.9993216

DO - 10.1109/CDC51059.2022.9993216

M3 - Conference contribution

AN - SCOPUS:85146987197

T3 - Proceedings of the IEEE Conference on Decision and Control

SP - 7547

EP - 7552

BT - 2022 IEEE 61st Conference on Decision and Control, CDC 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 61st IEEE Conference on Decision and Control, CDC 2022

Y2 - 6 December 2022 through 9 December 2022

ER -

Stability Via Adversarial Training of Neural Network Stochastic Control of Mean-Field Type

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this