Standard
Distributed Stochastic Optimization with Heavy-Ball Momentum Term for Parameter Estimation. / Erofeeva, Victoria; Granichin, Oleg; Sergeenko, Anna.
Conference Proceedings - 5th Scientific School Dynamics of Complex Networks and their Applications, DCNA 2021. ed. / Alexander Hramov; Semen Kurkin; Andrey Andreev; Natalia Shusharina. Institute of Electrical and Electronics Engineers Inc., 2021. p. 69-72 (Conference Proceedings - 5th Scientific School Dynamics of Complex Networks and their Applications, DCNA 2021).
Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Research › peer-review
Harvard
Erofeeva, V
, Granichin, O & Sergeenko, A 2021,
Distributed Stochastic Optimization with Heavy-Ball Momentum Term for Parameter Estimation. in A Hramov, S Kurkin, A Andreev & N Shusharina (eds),
Conference Proceedings - 5th Scientific School Dynamics of Complex Networks and their Applications, DCNA 2021. Conference Proceedings - 5th Scientific School Dynamics of Complex Networks and their Applications, DCNA 2021, Institute of Electrical and Electronics Engineers Inc., pp. 69-72, 5th Scientific School on Dynamics of Complex Networks and their Applications, DCNA 2021, Kaliningrad, Russian Federation,
13/09/21.
https://doi.org/10.1109/DCNA53427.2021.9586829,
https://doi.org/10.1109/DCNA53427.2021.9586829APA
Erofeeva, V.
, Granichin, O., & Sergeenko, A. (2021).
Distributed Stochastic Optimization with Heavy-Ball Momentum Term for Parameter Estimation. In A. Hramov, S. Kurkin, A. Andreev, & N. Shusharina (Eds.),
Conference Proceedings - 5th Scientific School Dynamics of Complex Networks and their Applications, DCNA 2021 (pp. 69-72). (Conference Proceedings - 5th Scientific School Dynamics of Complex Networks and their Applications, DCNA 2021). Institute of Electrical and Electronics Engineers Inc..
https://doi.org/10.1109/DCNA53427.2021.9586829,
https://doi.org/10.1109/DCNA53427.2021.9586829Vancouver
Erofeeva V
, Granichin O, Sergeenko A.
Distributed Stochastic Optimization with Heavy-Ball Momentum Term for Parameter Estimation. In Hramov A, Kurkin S, Andreev A, Shusharina N, editors, Conference Proceedings - 5th Scientific School Dynamics of Complex Networks and their Applications, DCNA 2021. Institute of Electrical and Electronics Engineers Inc. 2021. p. 69-72. (Conference Proceedings - 5th Scientific School Dynamics of Complex Networks and their Applications, DCNA 2021).
https://doi.org/10.1109/DCNA53427.2021.9586829,
https://doi.org/10.1109/DCNA53427.2021.9586829Author
BibTeX
@inproceedings{877be29540e14979963a9318e19444bc,
title = "Distributed Stochastic Optimization with Heavy-Ball Momentum Term for Parameter Estimation",
abstract = "In this paper, we analyze DSPSA: a new distributed optimization algorithm for problems involving uncertainties. DSPSA combines Simultaneous perturbation stochastic approximation with consensus protocol and possesses properties of both algorithms. We study this method in the context of parameter estimation problems over large-scale sensor networks. Optimization in such networks may lead to communication overhead. This problem sets new requirements on optimization algorithms that must account for the efficacy of communication. Despite the presence of uncertainties: noise, external disturbance, and time-varying topology due to communication constraints, DSPSA converges to parameters to be estimated. The theoretical results provide an asymptotically efficient upper bound for the residuals. We also ananyze the convergence of the algorithm with the involvmenet of the heavy-ball momemnum term.",
keywords = "Consensus, parameter estimation, SPSA",
author = "Victoria Erofeeva and Oleg Granichin and Anna Sergeenko",
note = "Publisher Copyright: {\textcopyright} 2021 IEEE; 5th Scientific School on Dynamics of Complex Networks and their Applications, DCNA 2021, DCNA 2021 ; Conference date: 13-09-2021 Through 15-09-2021",
year = "2021",
month = sep,
day = "13",
doi = "10.1109/DCNA53427.2021.9586829",
language = "English",
isbn = "978-1-6654-4284-8",
series = "Conference Proceedings - 5th Scientific School Dynamics of Complex Networks and their Applications, DCNA 2021",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "69--72",
editor = "Alexander Hramov and Semen Kurkin and Andrey Andreev and Natalia Shusharina",
booktitle = "Conference Proceedings - 5th Scientific School Dynamics of Complex Networks and their Applications, DCNA 2021",
address = "United States",
url = "http://bfnaics.kantiana.ru/",
}
RIS
TY - GEN
T1 - Distributed Stochastic Optimization with Heavy-Ball Momentum Term for Parameter Estimation
AU - Erofeeva, Victoria
AU - Granichin, Oleg
AU - Sergeenko, Anna
N1 - Publisher Copyright:
© 2021 IEEE
PY - 2021/9/13
Y1 - 2021/9/13
N2 - In this paper, we analyze DSPSA: a new distributed optimization algorithm for problems involving uncertainties. DSPSA combines Simultaneous perturbation stochastic approximation with consensus protocol and possesses properties of both algorithms. We study this method in the context of parameter estimation problems over large-scale sensor networks. Optimization in such networks may lead to communication overhead. This problem sets new requirements on optimization algorithms that must account for the efficacy of communication. Despite the presence of uncertainties: noise, external disturbance, and time-varying topology due to communication constraints, DSPSA converges to parameters to be estimated. The theoretical results provide an asymptotically efficient upper bound for the residuals. We also ananyze the convergence of the algorithm with the involvmenet of the heavy-ball momemnum term.
AB - In this paper, we analyze DSPSA: a new distributed optimization algorithm for problems involving uncertainties. DSPSA combines Simultaneous perturbation stochastic approximation with consensus protocol and possesses properties of both algorithms. We study this method in the context of parameter estimation problems over large-scale sensor networks. Optimization in such networks may lead to communication overhead. This problem sets new requirements on optimization algorithms that must account for the efficacy of communication. Despite the presence of uncertainties: noise, external disturbance, and time-varying topology due to communication constraints, DSPSA converges to parameters to be estimated. The theoretical results provide an asymptotically efficient upper bound for the residuals. We also ananyze the convergence of the algorithm with the involvmenet of the heavy-ball momemnum term.
KW - Consensus
KW - parameter estimation
KW - SPSA
UR - http://www.scopus.com/inward/record.url?scp=85126522040&partnerID=8YFLogxK
UR - https://www.mendeley.com/catalogue/b906707b-c10f-350c-bab9-2396e8a8f11e/
U2 - 10.1109/DCNA53427.2021.9586829
DO - 10.1109/DCNA53427.2021.9586829
M3 - Conference contribution
AN - SCOPUS:85126522040
SN - 978-1-6654-4284-8
T3 - Conference Proceedings - 5th Scientific School Dynamics of Complex Networks and their Applications, DCNA 2021
SP - 69
EP - 72
BT - Conference Proceedings - 5th Scientific School Dynamics of Complex Networks and their Applications, DCNA 2021
A2 - Hramov, Alexander
A2 - Kurkin, Semen
A2 - Andreev, Andrey
A2 - Shusharina, Natalia
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 5th Scientific School on Dynamics of Complex Networks and their Applications, DCNA 2021
Y2 - 13 September 2021 through 15 September 2021
ER -
