Robust Multi-agent Optimization: Coping with Byzantine Agents with Input Redundancy

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10083)

Abstract

This paper addresses the multi-agent optimization problem in which the agents try to collaboratively minimize \(\frac{1}{k}\sum _{i=1}^k h_i\) for a given choice of k input functions \(h_1, \ldots , h_k\). This problem finds its application in distributed machine learning, where the data set is too large to be processed and stored by a single machine. It has been shown that when the networked agents may suffer Byzantine faults, it is impossible to minimize \(\frac{1}{k}\sum _{i=1}^k h_i\) with no redundancy in the local cost functions.

We are interested in the impact of the local cost functions redundancy on the solvability of \(\frac{1}{k}\sum _{i=1}^k h_i\). In particular, we assume that the local cost function of each agent is formed as a convex combination of the k input functions \(h_1, \ldots , h_k\). Depending on the availability of side information at each agent, two slightly different variants are considered. We show that for a given graph, the problem can indeed be solved despite the presence of faulty agents. In particular, even in the absence of side information at each agent, when adequate redundancy is available in the optima of input functions, a distributed algorithm is proposed in which each agent carries minimal state across iterations.

Keywords

Distributed optimization Multi-agent network Coding theory Byzantine faults Redundancy Security 

References

  1. 1.
    Anthonisse, J., Tijms, H.: Exponential convergence of products of stochastic matrices. J. Math. Anal. Appl. 59(2), 360–364 (1977)MathSciNetCrossRefMATHGoogle Scholar
  2. 2.
    Candes, E.J., Tao, T.: Decoding by linear programming. IEEE Trans. Inf. Theory 51(12), 4203–4215 (2005)MathSciNetCrossRefMATHGoogle Scholar
  3. 3.
    Chatterjee, S., Seneta, E.: Towards consensus: some convergence theorems on repeated averaging. J. Appl. Probab. 14(1), 89–97 (1977)MathSciNetCrossRefMATHGoogle Scholar
  4. 4.
    Chaudhuri, S.: More choices allow more faults: set consensus problems in totally asynchronous systems. Inf. Comput. 105, 132–158 (1992)MathSciNetCrossRefMATHGoogle Scholar
  5. 5.
    Dolev, D., Lynch, N.A., Pinter, S.S., Stark, E.W., Weihl, W.E.: Reaching approximate agreement in the presence of faults. J. ACM 33(3), 499–516 (1986)MathSciNetCrossRefMATHGoogle Scholar
  6. 6.
    Duchi, J., Agarwal, A., Wainwright, M. Dual averaging for distributed optimization: convergence analysis and network scaling. IEEE Trans. Autom. Control (2012)Google Scholar
  7. 7.
    Fekete, A.D.: Asymptotically optimal algorithms for approximate agreement. Distrib. Comput. 4(1), 9–29 (1990)MathSciNetCrossRefGoogle Scholar
  8. 8.
    Friedman, R., Mostefaoui, A., Rajsbaum, S., Raynal, M.: Asynchronous agreement and its relation with error-correcting codes. IEEE Trans. Comput. 56(7), 865–875 (2007)MathSciNetCrossRefMATHGoogle Scholar
  9. 9.
    LeBlanc, H.J., Zhang, H., Sundaram, S., Koutsoukos, X.: Consensus of multi-agent networks in the presence of adversaries using only local information. In: Proceedings of the 1st International Conference on High Confidence Networked Systems, HiCoNS 2012, pp. 1–10. ACM, New York (2012)Google Scholar
  10. 10.
    Mostefaoui, A., Rajsbaum, S., Raynal, M.: Conditions on input vectors for consensus solvability in asynchronous distributed systems. J. ACM (JACM) 50(6), 922–954 (2003)MathSciNetCrossRefMATHGoogle Scholar
  11. 11.
    Mostefaoui, A., Rajsbaum, S., Raynal, M.: Using conditions to expedite consensus in synchronous distributed systems. In: Fich, F.E. (ed.) DISC 2003. LNCS, vol. 2848, pp. 249–263. Springer, Heidelberg (2003). doi:10.1007/978-3-540-39989-6_18 CrossRefGoogle Scholar
  12. 12.
    Mostefaoui, A., Rajsbaum, S., Raynal, M.: Synchronous condition-based consensus. Distrib. Comput. 18(5), 325–343 (2006)CrossRefMATHGoogle Scholar
  13. 13.
    Nedic, A., Olshevsky, A.: Distributed optimization over time-varying directed graphs. IEEE Trans. Autom. Control 60(3), 601–615 (2015)MathSciNetCrossRefGoogle Scholar
  14. 14.
    Nedic, A., Ozdaglar, A.: Distributed subgradient methods for multi-agent optimization. IEEE Trans. Autom. Control 54(1), 48–61 (2009)MathSciNetCrossRefMATHGoogle Scholar
  15. 15.
    Pease, M., Shostak, R., Lamport, L.: Reaching agreement in the presence of faults. J. ACM 27(2), 228–234 (1980)MathSciNetCrossRefMATHGoogle Scholar
  16. 16.
    Robbins, H., Siegmund, D.: A convergence theorem for non negative almost supermartingales and some applications. In: Lai, T., Siegmund, D. (eds.) Herbert Robbins Selected Papers, pp. 111–135. Springer, New York (1985)CrossRefGoogle Scholar
  17. 17.
    Su, L., Vaidya, N.: Byzantine multi-agent optimization: Part i. arXiv,abs/1506.04681 (2015)
  18. 18.
    Su, L., Vaidya, N.: Byzantine Multi-agent optimization: part II (2015)Google Scholar
  19. 19.
    Su, L., Vaidya, N.H.: Fault-tolerant multi-agent optimization: optimal iterative distributed algorithms. In: Proceedings of the ACM Symposium on Principles of Distributed Computing, pp. 425–434. ACM (2016)Google Scholar
  20. 20.
    Su, L., Vaidya, N.H.: Multi-agent optimization in the presence of byzantine adversaries: fundamental limits. In: Proceedings of IEEE American Control Conference (ACC), July 2016Google Scholar
  21. 21.
    Tsitsiklis, J.N., Bertsekas, D.P., Athans, M., et al.: Distributed asynchronous deterministic and stochastic gradient optimization algorithms. IEEE Trans. Autom. Control 31(9), 803–812 (1986)MathSciNetCrossRefMATHGoogle Scholar
  22. 22.
    Vaidya, N.H.: Matrix representation of iterative approximate Byzantine consensus in directed graphs. CoRR, abs/1203.1888 (2012)Google Scholar
  23. 23.
    Vaidya, N.H., Tseng, L., Liang, G.: Iterative approximate byzantine consensus in arbitrary directed graphs. In: Proceedings of ACM Symposium on Principles of Distributed Computing (PODC) (2012)Google Scholar

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  1. 1.Department of Electrical and Computer EngineeringUniversity of Illinois at Urbana-ChampaignUrbanaUSA

Personalised recommendations