Abstract
We consider a min-max optimization problem over a time-varying network of computational agents, where each agent in the network has its local convex cost function which is a private knowledge of the agent. The agents want to jointly minimize the maximum cost incurred by any agent in the network, while maintaining the privacy of their objective functions. To solve the problem, we consider subgradient algorithms where each agent computes its own estimates of an optimal point based on its own cost function, and it communicates these estimates to its neighbors in the network. The algorithms employ techniques from convex optimization, stochastic approximation and averaging protocols (typically used to ensure a proper information diffusion over a network), which allow time-varying network structure. We discuss two algorithms, one based on exact-penalty approach and the other based on primal-dual Lagrangian approach, where both approaches utilize Bregman-distance functions.We establish convergence of the algorithms (with probability one) for a diminishing step-size, and demonstrate the applicability of the algorithms by considering a power allocation problem in a cellular network.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Agarwal, A., Duchi, J., Wainwright, M.: Dual averaging for distributed optimization: Convergence analysis and network scaling. IEEE Transactions on Automatic Control (2011) (to appear)
Arrow, K.J., Hurwicz, L., Uzawa, H.: Studies in Linear and Non-Linear Programming. Stanford University Press, Stanford (1958)
Bertsekas, D.P.: Necessary and sufficient conditions for a penalty method to be exact. Mathematical Programming 9, 87–99 (1975)
Bertsekas, D.P., Nedić, A., Ozdaglar, A.: Convex Analysis and Optimization. Athena Scientific, Belmont (2003)
Bertsekas, D.P., Tsitsiklis, J.N.: Parallel and distributed computation: numerical methods. Prentice-Hall, Inc., Upper Saddle River (1989)
Bertsekas, D.P., Tsitsiklis, J.N.: Gradient convergence in gradient methods with errors. Siam. J. Optim. 10(3), 627–642 (2000)
Billingsley, P.: Probability and Measure. John Wiley and Sons (1979)
Boche, H., Wiczanowski, M., Stanczak, S.: Unifying view on min-max fairness and utility optimization in cellular networks. In: 2005 IEEE Wireless Communications and Networking Conference, vol. 3, pp. 1280–1285 (March 2005)
Borkar, V.S.: Stochastic Approximation: A Dynamical Systems Viewpoint. Cambridge University Press (2008)
Bregman, L.: The relaxation method of finding the common point of convex sets and its application to the solution of problems in convex programming. USSR Computational Mathematics and Mathematical Physics 7(3), 200–217 (1967)
Censor, Y.A., Zenios, S.A.: Parallel Optimization: Theory, Algorithms and Applications. Oxford University Press (1997)
Chiang, M., Hande, P., Lan, T., Tan, W.C.: Power Control in Wireless Cellular Networks. Found. Trends Netw. 2(4), 381–533 (2008)
Ermoliev, Y.: Stochastic quasi-gradient methods and their application to system optimization. Stochastics 9(1), 1–36 (1983)
Ermoliev, Y.: Stochastic quazigradient methods. In: Numerical Techniques for Stochastic Optimization, pp. 141–186. Springer, Heidelberg (1988)
Hastie, T., Tibshirani, R., Friedman, J.H.: The Elements of Statistical Learning. Springer (2003)
Jadbabaie, A., Lin, J., Morse, S.: Coordination of groups of mobile autonomous agents using nearest neighbor rules. IEEE Transactions on Automatic Control 48, 988–1001 (2003)
Johansson, B., Rabi, M., Johansson, M.: A randomized incremental subgradient method for distributed optimization in networked systems. SIAM Journal on Optimization 20(3), 1157–1170 (2009)
Kar, S., Moura, J.M.F.: Distributed consensus algorithms in sensor networks with imperfect communication: link failures and channel noise. IEEE Tran. Signal Process. 57(1), 355–369 (2009)
Lobel, I., Ozdaglar, A.: Distributed subgradient methods for convex optimization over random networks. IEEE Transactions on Automatic Control 56(6), 1291–1306 (2011)
Mosk-Aoyama, D., Roughgarden, T., Shah, D.: Fully Distributed Algorithms for Convex Optimization Problems. In: Pelc, A. (ed.) DISC 2007. LNCS, vol. 4731, pp. 492–493. Springer, Heidelberg (2007)
Nedić, A.: Asynchronous broadcast-based convex optimization over a network. IEEE Transactions on Automatic Control 56(6), 1337–1351 (2011)
Nedić, A., Olshevsky, A., Ozdaglar, A., Tsitsiklis, J.N.: Distributed subgradient algorithms and quantization effects. In: Proceedings of the 47th IEEE Conference on Decision and Control, pp. 4177–4184 (2008)
Nedić, A., Ozdaglar, A.: Distributed subgradient methods for multi-agent optimization. IEEE Transactions on Automatic Control 54(1), 48–61 (2009)
Nedić, A., Ozdaglar, A.: Subgradient methods for saddle-point problems. Journal of Optimization Theory and Applications 142(1), 205–228 (2009)
Nedić, A., Ozdaglar, A., Parrilo, P.A.: Constrained consensus and optimization in multi-agent networks. IEEE Transactions on Automatic Control 55, 922–938 (2010)
Nemirovski, A., Juditsky, A., Lan, G., Shapiro, A.: Robust stochastic approximation approach to stochastic programming. SIAM J. on Optimization 19(4), 1574–1609 (2008)
Polyak, B.T.: Introduction to Optimization. Optimization Software, Inc., New York (1987)
Rabbat, M., Nowak, R.D.: Distributed optimization in sensor networks. In: IPSN, pp. 20–27 (2004)
Ram, S.S., Nedić, A., Veeravalli, V.V.: Distributed stochastic subgradient projection algorithms for convex optimization. Journal of Optimization Theory and Applications 147(3), 516–545 (2010)
Ram, S.S., Veeravalli, V.V., Nedić, A.: Distributed non-autonomous power control through distributed convex optimization. In: IEEE INFOCOM, pp. 3001–3005 (2009)
Sundhar Ram, S., Nedić, A., Veeravalli, V.V.: Asynchronous gossip algorithms for stochastic optimization: Constant stepsize analysis. In: Diehl, M., Glineur, F., Jarlebring, E., Michiels, W. (eds.) Recent Advances in Optimization and its Applications in Engineering, 14th Belgian-French-German Conference on Optimization (BFG), pp. 51–60 (2010)
Ram, S.S., Nedić, A., Veeravalli, V.V.: A new class of distributed optimization algorithms: Application to regression of distributed data. Optimization Methods and Software 27(1), 71–88 (2012)
Robbins, H., Siegmund, D.: A convergence theorem for nonnegative almost supermartingales and some applications. In: Rustagi, J.S. (ed.) Proceedings of a Symposium on Optimizing Methods in Statistics, pp. 233–257. Academic Press, New York (1971)
Srikant, R.: The Mathematics of Internet Congestion Control. Birkhäuser, Boston (2003)
Srivastava, K., Nedić, A.: Distributed asynchronous constrained stochastic optimization. IEEE Journal of Selected Topics in Signal Processing 5(4), 772–790 (2011)
Srivastava, K., Nedić, A., Stipanović, D.: Distributed min-max optimization in networks. In: 17th International Conference on Digital Signal Processing (2011)
Stanković, S.S., Stanković, M.S., Stipanović, D.M.: Decentralized parameter estimation by consensus based stochastic approximation. In: 2007 46th IEEE Conference on Decision and Control, pp. 1535–1540 (December 2007)
Tsitsiklis, J.N.: Problems in decentralized decision making and computation. PhD thesis, Massachusetts Institute of Technology, Boston (1984)
Tsitsiklis, J.N., Athans, M.: Convergence and asymptotic agreement in distributed decision problems. IEEE Trans. Automat. Control 29, 42–50 (1984)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Srivastava, K., Nedić, A., Stipanović, D. (2013). Distributed Bregman-Distance Algorithms for Min-Max Optimization. In: Czarnowski, I., Jędrzejowicz, P., Kacprzyk, J. (eds) Agent-Based Optimization. Studies in Computational Intelligence, vol 456. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-34097-0_7
Download citation
DOI: https://doi.org/10.1007/978-3-642-34097-0_7
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-34096-3
Online ISBN: 978-3-642-34097-0
eBook Packages: EngineeringEngineering (R0)