Fixed-time Distributed Optimization under Time-Varying Communication Topology

This paper presents a method to solve distributed optimization problem within a fixed time over a time-varying communication topology. Each agent in the network can access its private objective function, while exchange of local information is permitted between the neighbors. This study investigates first nonlinear protocol for achieving distributed optimization for time-varying communication topology within a fixed time independent of the initial conditions. For the case when the global objective function is strictly convex, a second-order Hessian based approach is developed for achieving fixed-time convergence. In the special case of strongly convex global objective function, it is shown that the requirement to transmit Hessians can be relaxed and an equivalent first-order method is developed for achieving fixed-time convergence to global optimum. Results are further extended to the case where the underlying team objective function, possibly non-convex, satisfies only the Polyak-Łojasiewicz (PL) inequality, which is a relaxation of strong convexity.

[1]  Zhengtao Ding,et al.  Fixed-Time Consensus Tracking for Multiagent Systems With High-Order Integrator Dynamics , 2018, IEEE Transactions on Automatic Control.

[2]  Magnus Egerstedt,et al.  Graph Theoretic Methods in Multiagent Networks , 2010, Princeton Series in Applied Mathematics.

[3]  Jun Wang,et al.  A projection neural network and its application to constrained optimization problems , 2002 .

[4]  Dennis S. Bernstein,et al.  Finite-Time Stability of Continuous Autonomous Systems , 2000, SIAM J. Control. Optim..

[5]  Guoqiang Hu,et al.  Finite-time distributed optimization with quadratic objective functions under uncertain information , 2017, 2017 IEEE 56th Annual Conference on Decision and Control (CDC).

[6]  Lihua Xie,et al.  Continuous-time Distributed Convex Optimization with Set Constraints , 2014 .

[7]  Zengqiang Chen,et al.  Distributed Optimization with Finite-Time Convergence via Discontinuous Dynamics , 2018, 2018 37th Chinese Control Conference (CCC).

[8]  Robert Nowak,et al.  Distributed optimization in sensor networks , 2004, Third International Symposium on Information Processing in Sensor Networks, 2004. IPSN 2004.

[9]  Lei Wang,et al.  Finite-time consensus of multi-agent systems with continuous time-varying interaction topology , 2018, Neurocomputing.

[10]  Sergey Parsegov,et al.  Fixed-time consensus algorithm for multi-agent systems with integrator dynamics , 2013 .

[11]  Weisheng Chen,et al.  Finite-time convergent distributed consensus optimisation over networks , 2016 .

[12]  Diego Klabjan,et al.  Optimization for Large-Scale Machine Learning with Distributed Features and Observations , 2017, MLDM.

[13]  Alfred O. Hero,et al.  A Convergent Incremental Gradient Method with a Constant Step Size , 2007, SIAM J. Optim..

[14]  Boi Faltings,et al.  PC-DPOP: A New Partial Centralization Algorithm for Distributed Optimization , 2007, IJCAI.

[15]  Jiong Jin,et al.  Fixed-time consensus for multi-agent systems with discontinuous inherent dynamics over switching topology , 2017, Int. J. Syst. Sci..

[16]  Juan Li,et al.  Fixed-time consensus of multi-agent system under time varying topology , 2017, IECON 2017 - 43rd Annual Conference of the IEEE Industrial Electronics Society.

[17]  Angelia Nedic,et al.  Distributed Optimization Over Time-Varying Directed Graphs , 2015, IEEE Trans. Autom. Control..

[18]  Gang Chen,et al.  A fixed-time convergent algorithm for distributed convex optimization in multi-agent systems , 2018, Autom..

[19]  Jay A. Farrell,et al.  Distributed Continuous-Time Optimization: Nonuniform Gradient Gains, Finite-Time Convergence, and Convex Constraint Set , 2017, IEEE Transactions on Automatic Control.

[20]  Huai-Ning Wu,et al.  Leader-following formation control of multi-agent systems under fixed and switching topologies , 2012, Int. J. Control.

[21]  Jiaqi Zhang,et al.  Distributed Adaptive Newton Methods with Globally Superlinear Convergence , 2020, ArXiv.

[22]  Qing-Long Han,et al.  Distributed Optimization for Multiagent Systems: An Edge-Based Fixed-Time Consensus Approach , 2019, IEEE Transactions on Cybernetics.

[23]  John J. Hopfield,et al.  Simple 'neural' optimization networks: An A/D converter, signal decision circuit, and a linear programming circuit , 1986 .

[24]  Qinglei Hu,et al.  Smooth finite-time fault-tolerant attitude tracking control for rigid spacecraft , 2016 .

[25]  Asuman E. Ozdaglar,et al.  Constrained Consensus and Optimization in Multi-Agent Networks , 2008, IEEE Transactions on Automatic Control.

[26]  Dimitra Panagou,et al.  Fixed-Time Stable Gradient Flows: Applications to Continuous-Time Optimization , 2018, IEEE Transactions on Automatic Control.

[27]  Mark W. Schmidt,et al.  Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-Łojasiewicz Condition , 2016, ECML/PKDD.

[28]  Zongyu Zuo,et al.  Nonsingular fixed-time consensus tracking for second-order multi-agent networks , 2015, Autom..

[29]  Andrey Polyakov,et al.  Consistent Discretization of Finite-Time and Fixed-Time Stable Systems , 2019, SIAM J. Control. Optim..

[30]  Takatoshi Ito,et al.  A Filippov solution of a system of differential equations with discontinuous right-hand sides , 1979 .

[31]  Choon Yik Tang,et al.  Zero-gradient-sum algorithms for distributed convex optimization: The continuous-time case , 2011, Proceedings of the 2011 American Control Conference.

[32]  Stephen P. Boyd,et al.  A Differential Equation for Modeling Nesterov's Accelerated Gradient Method: Theory and Insights , 2014, J. Mach. Learn. Res..

[33]  Mihailo R. Jovanovic,et al.  Proximal gradient flow and Douglas-Rachford splitting dynamics: global exponential stability via integral quadratic constraints , 2021, Autom..

[34]  Wei Shi,et al.  Achieving Geometric Convergence for Distributed Optimization Over Time-Varying Graphs , 2016, SIAM J. Optim..

[35]  Jianying Yang,et al.  Distributed finite-time optimization for second order continuous-time multiple agents systems with time-varying cost function , 2018, Neurocomputing.

[36]  Zongyu Zuo,et al.  Distributed robust finite-time nonlinear consensus protocols for multi-agent systems , 2016, Int. J. Syst. Sci..

[37]  Jing Wang,et al.  A control perspective for centralized and distributed convex optimization , 2011, IEEE Conference on Decision and Control and European Control Conference.

[38]  Milind Tambe,et al.  Quality Guarantees on k-Optimal Solutions for Distributed Constraint Optimization Problems , 2007, IJCAI.

[39]  Andrey Polyakov,et al.  Nonlinear Feedback Design for Fixed-Time Stabilization of Linear Control Systems , 2012, IEEE Transactions on Automatic Control.