Gradient-Free Multi-Agent Nonconvex Nonsmooth Optimization

In this paper, we consider the problem of minimizing the sum of nonconvex and possibly nonsmooth functions over a connected multi-agent network, where the agents have partial knowledge about the global cost function and can only access the zeroth-order information (i.e., the functional values) of their local cost functions. We propose and analyze a distributed primal-dual gradient-free algorithm for this challenging problem. We show that by appropriately choosing the parameters, the proposed algorithm converges to the set of first order stationary solutions with a provable global sublinear convergence rate. Numerical experiments demonstrate the effectiveness of the proposed method for optimizing nonconvex and nonsmooth problems over a network.

[1]  Zhi-Quan Luo,et al.  A Unified Algorithmic Framework for Block-Structured Optimization Involving Big Data: With applications in machine learning and signal processing , 2015, IEEE Signal Processing Magazine.

[2]  Mingyi Hong,et al.  ZONE: Zeroth-Order Nonconvex Multiagent Optimization Over Networks , 2017, IEEE Transactions on Automatic Control.

[3]  Stephen P. Boyd,et al.  Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers , 2011, Found. Trends Mach. Learn..

[4]  Saeed Ghadimi,et al.  Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming , 2013, SIAM J. Optim..

[5]  Michael M. Zavlanos,et al.  Approximate projections for decentralized optimization with SDP constraints , 2015, 2016 IEEE 55th Conference on Decision and Control (CDC).

[6]  John N. Tsitsiklis,et al.  On distributed averaging algorithms and quantization effects , 2007, 2008 47th IEEE Conference on Decision and Control.

[7]  Zhaoran Wang,et al.  NESTT: A Nonconvex Primal-Dual Splitting Method for Distributed and Stochastic Optimization , 2016, NIPS.

[8]  Asuman E. Ozdaglar,et al.  Distributed Subgradient Methods for Multi-Agent Optimization , 2009, IEEE Transactions on Automatic Control.

[9]  Shengyuan Xu,et al.  Gradient‐free method for distributed multi‐agent optimization via push‐sum algorithms , 2015 .

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

[11]  Mingyi Hong,et al.  Nonconvex alternating direction method of multipliers for distributed sparse principal component analysis , 2015, 2015 IEEE Global Conference on Signal and Information Processing (GlobalSIP).

[12]  Qing Ling,et al.  EXTRA: An Exact First-Order Algorithm for Decentralized Consensus Optimization , 2014, 1404.6264.

[13]  Michael M. Zavlanos,et al.  Complexity Certification of a Distributed Augmented Lagrangian Method , 2017, IEEE Transactions on Automatic Control.

[14]  Kin K. Leung,et al.  A Non-Convex Distributed Optimization Framework and its Application to Wireless Ad-hoc Networks , 2013, IEEE Transactions on Wireless Communications.

[15]  Lin Xiao,et al.  Optimal Algorithms for Online Convex Optimization with Multi-Point Bandit Feedback. , 2010, COLT 2010.

[16]  Behrouz Touri,et al.  Non-Convex Distributed Optimization , 2015, IEEE Transactions on Automatic Control.

[17]  Mehmet E. Yildiz,et al.  Coding With Side Information for Rate-Constrained Consensus , 2008, IEEE Transactions on Signal Processing.

[18]  Mingyi Hong,et al.  Prox-PDA: The Proximal Primal-Dual Algorithm for Fast Distributed Nonconvex Optimization and Learning Over Networks , 2017, ICML.

[19]  Michael M. Zavlanos,et al.  On the Convergence of a Distributed Augmented Lagrangian Method for Nonconvex Optimization , 2017, IEEE Transactions on Automatic Control.

[20]  Daniel W. C. Ho,et al.  Randomized Gradient-Free Method for Multiagent Optimization Over Time-Varying Networks , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[21]  Qingjiang Shi,et al.  Alternating direction method of multipliers for a class of nonconvex bilinear optimization: convergence analysis and applications , 2017, Journal of Global Optimization.

[22]  Daniel Pérez Palomar,et al.  Distributed nonconvex multiagent optimization over time-varying networks , 2016, 2016 50th Asilomar Conference on Signals, Systems and Computers.

[23]  Martin J. Wainwright,et al.  Optimal Rates for Zero-Order Convex Optimization: The Power of Two Function Evaluations , 2013, IEEE Transactions on Information Theory.

[24]  Darinka Dentcheva,et al.  An augmented Lagrangian method for distributed optimization , 2014, Mathematical Programming.

[25]  Michael M. Zavlanos,et al.  A Distributed Algorithm for Convex Constrained Optimization Under Noise , 2016, IEEE Transactions on Automatic Control.

[26]  M. Reza Peyghami,et al.  A relaxed nonmonotone adaptive trust region method for solving unconstrained optimization problems , 2015, Comput. Optim. Appl..

[27]  Gesualdo Scutari,et al.  NEXT: In-Network Nonconvex Optimization , 2016, IEEE Transactions on Signal and Information Processing over Networks.

[28]  Shengyuan Xu,et al.  Zeroth-Order Method for Distributed Optimization With Approximate Projections , 2016, IEEE Transactions on Neural Networks and Learning Systems.

[29]  Cho-Jui Hsieh,et al.  A Comprehensive Linear Speedup Analysis for Asynchronous Stochastic Parallel Optimization from Zeroth-Order to First-Order , 2016, NIPS.

[30]  Asuman E. Ozdaglar,et al.  On the Convergence Rate of Incremental Aggregated Gradient Algorithms , 2015, SIAM J. Optim..

[31]  I. Gijbels,et al.  Penalized likelihood regression for generalized linear models with non-quadratic penalties , 2011 .

[32]  Yurii Nesterov,et al.  Random Gradient-Free Minimization of Convex Functions , 2015, Foundations of Computational Mathematics.

[33]  Asuman E. Ozdaglar,et al.  Distributed Subgradient Methods for Convex Optimization Over Random Networks , 2011, IEEE Transactions on Automatic Control.

[34]  James C. Spall,et al.  Introduction to Stochastic Search and Optimization. Estimation, Simulation, and Control (Spall, J.C. , 2007 .

[35]  Emil Björnson,et al.  Optimal Resource Allocation in Coordinated Multi-Cell Systems , 2013, Found. Trends Commun. Inf. Theory.

[36]  Pascal Bianchi,et al.  Convergence of a Multi-Agent Projected Stochastic Gradient Algorithm for Non-Convex Optimization , 2011, IEEE Transactions on Automatic Control.

[37]  M. Reza Peyghami,et al.  A nonmonotone PRP conjugate gradient method for solving square and under-determined systems of equations , 2017, Comput. Math. Appl..

[38]  Alejandro Ribeiro,et al.  Network Integrity in Mobile Robotic Networks , 2013, IEEE Transactions on Automatic Control.

[39]  James C. Spall,et al.  Introduction to stochastic search and optimization - estimation, simulation, and control , 2003, Wiley-Interscience series in discrete mathematics and optimization.

[40]  Volkan Cevher,et al.  Convex Optimization for Big Data: Scalable, randomized, and parallel algorithms for big data analytics , 2014, IEEE Signal Processing Magazine.