TY - GEN
T1 - Inexact-Proximal Accelerated Gradient Method for Stochastic Nonconvex Constrained Optimization Problems
AU - Boroun, Morteza
AU - Jalilzadeh, Afrooz
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - Stochastic nonconvex optimization problems with nonlinear constraints have a broad range of applications in intelligent transportation, cyber-security, and smart grids. In this paper, first, we propose an inexact-proximal accelerated gradient method to solve a nonconvex stochastic composite optimization problem where the objective is the sum of smooth and nonsmooth functions, the constraint functions are assumed to be deterministic and the solution to the proximal map of the nonsmooth part is calculated inexactly at each iteration. We demonstrate an asymptotic sublinear rate of convergence for stochastic settings using increasing sample-size considering the error in the proximal operator diminishes at an appropriate rate. Then we customize the proposed method for solving stochastic nonconvex optimization problems with nonlinear constraints and demonstrate a convergence rate guarantee. Numerical results show the effectiveness of the proposed algorithm.
AB - Stochastic nonconvex optimization problems with nonlinear constraints have a broad range of applications in intelligent transportation, cyber-security, and smart grids. In this paper, first, we propose an inexact-proximal accelerated gradient method to solve a nonconvex stochastic composite optimization problem where the objective is the sum of smooth and nonsmooth functions, the constraint functions are assumed to be deterministic and the solution to the proximal map of the nonsmooth part is calculated inexactly at each iteration. We demonstrate an asymptotic sublinear rate of convergence for stochastic settings using increasing sample-size considering the error in the proximal operator diminishes at an appropriate rate. Then we customize the proposed method for solving stochastic nonconvex optimization problems with nonlinear constraints and demonstrate a convergence rate guarantee. Numerical results show the effectiveness of the proposed algorithm.
UR - http://www.scopus.com/inward/record.url?scp=85126116589&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85126116589&partnerID=8YFLogxK
U2 - 10.1109/WSC52266.2021.9715404
DO - 10.1109/WSC52266.2021.9715404
M3 - Conference contribution
AN - SCOPUS:85126116589
T3 - Proceedings - Winter Simulation Conference
BT - 2021 Winter Simulation Conference, WSC 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2021 Winter Simulation Conference, WSC 2021
Y2 - 12 December 2021 through 15 December 2021
ER -