A Saddle Point Algorithm for Networked Online Convex Optimization

IEEE Transactions on Signal Processing

Volumn 63, Issue 19, 2015, Pages 5149-5164

  Koppel, Alec ^a   Jakubiec, Felicia Y ^a   Ribeiro, Alejandro ^a  

^a UNIVERSITY OF PENNSYLVANIA   (United States)

Author keywords

convex optimization; Distributed optimization; multiagent systems; online learning; regret bounds; saddle point method

Indexed keywords

CONVEX OPTIMIZATION; COST FUNCTIONS; E-LEARNING; LAGRANGE MULTIPLIERS; MULTI AGENT SYSTEMS; NETWORK SECURITY; ONLINE SYSTEMS; SOCIAL NETWORKING (ONLINE);

DISTRIBUTED OPTIMIZATION; NEIGHBORING NODES; ONLINE CONVEX OPTIMIZATIONS; ONLINE LEARNING; RECURSIVE LEAST SQUARE (RLS); REGRET BOUNDS; SADDLEPOINT METHOD; SERVICE PROVIDER;

ALGORITHMS;

EID: 84941072304     PISSN: 1053587X     EISSN: None     Source Type: Journal    
DOI: 10.1109/TSP.2015.2449255     Document Type: Article

References (32)

1. A. Koppel, F. Y. Jakubiec, and A. Ribeiro, "A saddle point algorithm for networked online convex optimization," in Proc. Int. Conf. Acoust., Speech, Signal Process., May 4-9, 2014, pp. 8292-8296.
2. S. Shalev-Shwartz, "Online learning and online convex optimization," Found. Trends Mach. Learn., vol. 4, no. 2, pp. 107-194, Feb. 2012.
3. V. N. Vapnik, The Nature of Statistical Learning Theory. New York, NY, USA: Springer-Verlag, 1995.
4. M. Zinkevich, "Online convex programming and generalized infinitesimal gradient ascent," in Proc. 20th Int. Conf. Mach. Learn., Washington, DC, USA, Aug. 21-24, 2003, vol. 20, no. 2, pp. 928-936.
5. C. B. Do, Q. V. Le, and C.-S. Foo, "Proximal regularization for online and batch learning," in Proc. 26th ACM Int. Conf. Mach. Learn., New York, NY, USA, Jun. 14-18, 2009, pp. 257-264.
6. S. Shalev-Shwartz and Y. Singer, "Logarithmic regret algorithms for strongly convex repeated games," The Hebrew Univ., Jerusalem, Israel, Tech. Rep., 2007.
7. S. Ram, A. Nedi?, and V. Veeravalli, "Distributed stochastic subgradient projection algorithms for convex optimization," J Optim. Theory App., vol. 147, no. 3, pp. 516-545, Sep. 2010.
8. T. Suzuki, "Dual averaging and proximal gradient descent for online alternating direction multiplier method," in Proc. 30th Int. Conf. Mach. Learn., Atlanta, GA, USA, Jun. 16-21, 2013, vol. 28, no. 1, pp. 392-400.
9. A. Nedi? and A. Ozdaglar, "Subgradient methods for saddle-point problems," J Optim. Theory Appl., vol. 142, no. 1, pp. 205-228, Aug. 2009.
10. D. Jakovetic, J. M. F. Xavier, and J. M. F. Moura, "Fast distributed gradient methods," Apr. 2011, abs/1112. 2972 [Online]. Available: http:// arxiv. org/abs/1112. 2972
11. K. Yuan, Q. Ling, and W. Yin, "On the convergence of decentralized gradient descent," Oct. 2013, ArXiv e-prints 1310. 7063 [Online]. Available: http://arxiv. org/abs/1310. 7063
12. M. Rabbat, R. Nowak, and J. Bucklew, "Generalized consensus computation in networked systems with erasure links," in Proc. IEEE 6th Workshop Signal Process. Adv. Wireless Commun Process., Jun. 5-8, 2005, pp. 1088-1092.
13. F. Jakubiec and A. Ribeiro, "DMAP distributed maximum a posteriori probability estimation of dynamic systems," IEEE Trans. Signal Process., vol. 61, no. 2, pp. 450-466, Feb. 2013.
14. I. Schizas, A. Ribeiro, and G. Giannakis, "Consensus in ad hoc WSNs with noisy links-Part I: Distributed estimation of deterministic signals," IEEE Trans. Signal Process., vol. 56, no. 1, pp. 350-364, Jan. 2008.
15. Q. Ling, W. Shi, G. Wu, and A. Ribeiro, "DLM: Decentralized linearized alternating direction method of multipliers," IEEE Trans. Signal Process., vol. 63, no. 15, pp. 4051-4064, Aug. 2014.
16. M. Zargham, A. Ribeiro, A. Jadbabaie, and A. Ozdaglar, "Accelerated dual descent for network optimization," IEEE Trans. Autom. Control, vol. 59, no. 4, pp. 905-920, Apr. 2014.
17. K. Arrow, L. Hurwicz, and H. Uzawa, Studies in Linear and Non-Linear Programming, ser. Stanford Math. Studies in the Social Sci. Stanford, CA, USA: Stanford Univ. Press, Dec. 1958, vol. II.
18. Y. Nesterov, "Primal-dual subgradient methods for convex problems," Math. Program., vol. 120, no. 1, pp. 221-259, Apr. 2009.
19. K. I. Tsianos and M. G. Rabbat, "Distributed strongly convex optimization," Jul. 2012, abs/1207. 3031 [Online]. Available: http://arxiv. org/ abs/1207. 3031
20. F. Yan, S. V. N. Vishwanathan, and Y. Qi, "Cooperative autonomous online learning," Sep. 2010, abs/1006. 4039 [Online]. Available: http:/ /arxiv. org/abs/1006. 4039v1
21. A. Nedi and A. Ozdaglar, "Approximate primal solutions and rate analysis for dual subgradient methods," SIAM J. Optim., vol. 19, no. 4, pp. 1757-1780, Feb. 2009.
22. I. Lobel and A. Ozdaglar, "Distributed subgradient methods for convex optimization over random networks," IEEE Trans. Autom. Control, vol. 56, no. 6, pp. 1291-1306, Jun. 2011.
23. C. J. C. Burges, "A tutorial on support vector machines for pattern recognition," Data Min. Knowl. Discov., vol. 2, no. 2, pp. 121-167, Jun. 1998.
24. H. D. Block, "The perceptron: A model for brain functioning. Part I," Rev. Mod. Phys., vol. 34, pp. 123-135, Jan. 1962.
25. Y. Freund and R. E. Schapire, "Large margin classification using the perceptron algorithm," Mach. Learn., vol. 37, no. 3, pp. 277-296, Dec. 1999.
26. D. J. Watts and S. H. Strogatz, "Collective dynamics of 'small-world' networks," Nature, vol. 393, no. 6684, pp. 440-442, Jun. 1998.
27. D. B. West, Introduction to Graph Theory, 2nd ed. Englewood Cliffs, NJ, USA: Prentice-Hall, Sep. 2000.
28. F. Yan, S. Sundaram, S. V. N. Vishwanathan, and Y. Qi, "Distributed autonomous online learning: Regrets and intrinsic privacy-preserving properties," IEEE Trans. Knowl. Data Eng., vol. 25, no. 11, pp. 2483-2493, Nov. 2013.
29. K. Bache and M. Lichman, KDD Cup 1999 Data, 2013 [Online]. Available: http://archive. ics. uci. edu/ml/databases/kddcup99/kddcup99. html
30. M. Tavallaee, E. Bagheri, W. Lu, and A. A. Ghorbani, "A detailed analysis of the KDD Cup 99 data set," in IEEE Proc. Int. Symp. Comput. Intell. Sec. Def. Appl., Ottawa, ON, Canada, Jul. 8-10, 2009, pp. 53-58.
31. R.-E. Fan, K.-W. Chang, C.-J. Hsieh, X.-R. Wang, and C.-J. Lin, "LIBLINEAR: A library for large linear classification," J. Mach. Learn. Res., vol. 9, pp. 1871-1874, Aug. 2008.
32. P. Shi and C.-L. Tsai, "Regression model selection-a residual likelihood approach," J. Roy. Statist. Soc. Ser. B, vol. 64, no. 2, pp. 237-252, May 2002.