Random Coordinate Descent Algorithms for Multi-Agent Convex Optimization Over Networks

In this paper, we develop randomized block-coordinate descent methods for minimizing multi-agent convex optimization problems with linearly coupled constraints over networks and prove that they obtain in expectation an ε accurate solution in at most O(1/λ2(Q)ϵ) iterations, where λ2(Q) is the second smallest eigenvalue of a matrix Q that is defined in terms of the probabilities and the number of blocks. However, the computational complexity per iteration of our methods is much simpler than the one of a method based on full gradient information and each iteration can be computed in a completely distributed way. We focus on how to choose the probabilities to make these randomized algorithms to converge as fast as possible and we arrive at solving a sparse SDP. Analysis for rate of convergence in probability is also provided. For strongly convex functions our distributed algorithms converge linearly. We also extend the main algorithm to a more general random coordinate descent method and to problems with more general linearly coupled constraints. Preliminary numerical tests confirm that on very large optimization problems our method is much more numerically efficient than methods based on full gradient.

[1]  David Thomas,et al.  The Art in Computer Programming , 2001 .

[2]  Asuman E. Ozdaglar,et al.  A distributed Newton method for Network Utility Maximization , 2010, 49th IEEE Conference on Decision and Control (CDC).

[3]  Yurii Nesterov,et al.  Introductory Lectures on Convex Optimization - A Basic Course , 2014, Applied Optimization.

[4]  Yurii Nesterov,et al.  Efficiency of Coordinate Descent Methods on Huge-Scale Optimization Problems , 2012, SIAM J. Optim..

[5]  Paul Tseng,et al.  A coordinate gradient descent method for nonsmooth separable minimization , 2008, Math. Program..

[6]  Michael D. Vose,et al.  A Linear Algorithm For Generating Random Numbers With a Given Distribution , 1991, IEEE Trans. Software Eng..

[7]  L. Hurwicz.  Studies in Resource Allocation Processes: The design of resource allocation mechanisms , 1977 .

[8]  Yu-Chi Ho,et al.  A Class of Center-Free Resource Allocation Algorithms 1 , 1980 .

[9]  Stephen J. Wright.  Accelerated Block-coordinate Relaxation for Regularized Optimization , 2012, SIAM J. Optim..

[10]  P. Tseng,et al.  Block-Coordinate Gradient Descent Method for Linearly Constrained Nonsmooth Separable Optimization , 2009 .

[11]  L. Hurwicz.  The Design of Mechanisms for Resource Allocation , 1973 .

[12]  M. Moonen,et al.  Improved Dual Decomposition Based Optimization for DSL Dynamic Spectrum Management , 2010, IEEE Transactions on Signal Processing.

[13]  Rahul Simha,et al.  A Microeconomic Approach to Optimal Resource Allocation in Distributed Computer Systems , 1989, IEEE Trans. Computers.

[14]  Chia-Hua Ho,et al.  Recent Advances of Large-Scale Linear Classification , 2012, Proceedings of the IEEE.

[15]  Kim-Chuan Toh,et al.  A coordinate gradient descent method for ℓ1-regularized convex minimization , 2011, Comput. Optim. Appl..

[16]  Katya Scheinberg,et al.  Noname manuscript No. (will be inserted by the editor) Efficient Block-coordinate Descent Algorithms for the Group Lasso , 2022 .

[17]  S. Osher,et al.  Coordinate descent optimization for l 1 minimization with application to compressed sensing; a greedy algorithm , 2009 .

[18]  Adrian A Canutescu,et al.  Cyclic coordinate descent: A robotics algorithm for protein loop closure , 2003, Protein science : a publication of the Protein Society.

[19]  Gongyun Zhao,et al.  A Lagrangian Dual Method with Self-Concordant Barriers for Multi-Stage Stochastic Convex Programming , 2005, Math. Program..

[20]  Stephen P. Boyd,et al.  Optimal Scaling of a Gradient Method for Distributed Resource Allocation , 2006 .

[21]  Chih-Jen Lin,et al.  Coordinate Descent Method for Large-scale L2-loss Linear Support Vector Machines , 2008, J. Mach. Learn. Res..

[22]  Gordon F. Royle,et al.  Algebraic Graph Theory , 2001, Graduate texts in mathematics.

[23]  Shiqian Ma,et al.  Fast Multiple-Splitting Algorithms for Convex Optimization , 2009, SIAM J. Optim..

[24]  YunSangwoon,et al.  A coordinate gradient descent method for l1-regularized convex minimization , 2011 .

[25]  Dimitri P. Bertsekas,et al.  Nonlinear Programming , 1997 .

[26]  Peter Richtárik,et al.  Iteration complexity of randomized block-coordinate descent methods for minimizing a composite function , 2011, Mathematical Programming.

[27]  G. Heal.  Planning without Prices , 1969 .

[28]  Y. Nesterov,et al.  A RANDOM COORDINATE DESCENT METHOD ON LARGE-SCALE OPTIMIZATION PROBLEMS WITH LINEAR CONSTRAINTS , 2013 .