Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
139 tokens/sec
GPT-4o
47 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Scalable Distributed Optimization of Multi-Dimensional Functions Despite Byzantine Adversaries (2403.06502v2)

Published 11 Mar 2024 in cs.MA and math.OC

Abstract: The problem of distributed optimization requires a group of networked agents to compute a parameter that minimizes the average of their local cost functions. While there are a variety of distributed optimization algorithms that can solve this problem, they are typically vulnerable to "Byzantine" agents that do not follow the algorithm. Recent attempts to address this issue focus on single dimensional functions, or assume certain statistical properties of the functions at the agents. In this paper, we provide two resilient, scalable, distributed optimization algorithms for multi-dimensional functions. Our schemes involve two filters, (1) a distance-based filter and (2) a min-max filter, which each remove neighborhood states that are extreme (defined precisely in our algorithms) at each iteration. We show that these algorithms can mitigate the impact of up to $F$ (unknown) Byzantine agents in the neighborhood of each regular agent. In particular, we show that if the network topology satisfies certain conditions, all of the regular agents' states are guaranteed to converge to a bounded region that contains the minimizer of the average of the regular agents' functions.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (53)
  1. Distributed asynchronous deterministic and stochastic gradient optimization algorithms. IEEE transactions on automatic control, 31(9):803–812, 1986.
  2. Optimal scaling of a gradient method for distributed resource allocation. Journal of optimization theory and applications, 129(3):469–488, 2006.
  3. A control perspective for centralized and distributed convex optimization. In 2011 50th IEEE conference on decision and control and European control conference, pages 3800–3805. IEEE, 2011.
  4. Distributed optimization and statistical learning via the alternating direction method of multipliers. Foundations and Trends® in Machine learning, 3(1):1–122, 2011.
  5. Decentralized quasi-newton methods. IEEE Transactions on Signal Processing, 65(10):2613–2628, 2017.
  6. Frost—fast row-stochastic optimization with uncoordinated step-sizes. EURASIP Journal on Advances in Signal Processing, 2019(1):1, 2019.
  7. On distributed convex optimization under inequality and equality constraints. IEEE Transactions on Automatic Control, 57(1):151–164, 2011.
  8. Distributed optimization over time-varying directed graphs. IEEE Transactions on Automatic Control, 60(3):601–615, 2014.
  9. On nonconvex decentralized gradient descent. IEEE Transactions on signal processing, 66(11):2834–2848, 2018.
  10. Distributed optimization under adversarial nodes. IEEE Transactions on Automatic Control, 64(3):1063–1076, 2018.
  11. A case of distributed optimization in adversarial environment. In IEEE International Conference on Acoustics, Speech and Signal Processing, pages 5252–5256, 2019.
  12. Data injection attack on decentralized optimization. In IEEE Int. Conf. on Acoustics, Speech and Signal Processing, pages 3644–3648, 2018.
  13. Byzantine multi-agent optimization: Part i. arXiv preprint arXiv:1506.04681, 2015.
  14. Fault-tolerant multi-agent optimization: optimal iterative distributed algorithms. In ACM Symposium on Principles of Distributed Computing, pages 425–434, 2016.
  15. Resilient distributed optimization algorithm against adversarial attacks. IEEE Transactions on Automatic Control, 65(10):4308–4315, 2019.
  16. On the location of the minimizer of the sum of two strongly convex functions. In IEEE Conference on Decision and Control (CDC), pages 1769–1774, 2018.
  17. Byzantine fault tolerant distributed linear regression. arXiv preprint arXiv:1903.08752, 2019.
  18. Machine learning with adversaries: Byzantine tolerant gradient descent. In Advances in Neural Information Processing Systems, pages 119–129, 2017.
  19. Robust aggregation for federated learning. IEEE Transactions on Signal Processing, 70:1142–1154, 2022.
  20. Byrdie: Byzantine-resilient distributed coordinate descent for decentralized learning. IEEE Transactions on Signal and Information Processing over Networks, 2019.
  21. Bridge: Byzantine-resilient decentralized gradient descent. IEEE Transactions on Signal and Information Processing over Networks, 8:610–626, 2022.
  22. Basil: A fast and Byzantine-resilient approach for decentralized training. IEEE Journal on Selected Areas in Communications, 40(9):2694–2716, 2022.
  23. Towards byzantine-resilient learning in decentralized systems. arXiv preprint arXiv:2002.08569, 2020.
  24. Byzantine fault-tolerance in decentralized optimization under 2f-redundancy. In 2021 American Control Conference (ACC), pages 3632–3637. IEEE, 2021.
  25. Detection and isolation of adversaries in decentralized optimization for non-strongly convex objectives. IFAC-PapersOnLine, 52(20):381–386, 2019.
  26. Byzantine-resilient decentralized stochastic optimization with robust aggregation rules. IEEE Transactions on Signal Processing, 2023.
  27. On the geometric convergence of byzantine-resilient distributed optimization algorithms. arXiv preprint arXiv:2305.10810, 2023a.
  28. Byzantine-resilient distributed optimization of multi-dimensional functions. In 2020 American Control Conference (ACC), pages 4399–4404. IEEE, 2020.
  29. Resilient asymptotic consensus in robust networks. IEEE Journal on Selected Areas in Communications, 31(4):766–781, 2013.
  30. Byzantine-resilient multiagent optimization. IEEE Transactions on Automatic Control, 66(5):2227–2233, 2020.
  31. Alistair Sinclair. Improved bounds for mixing rates of markov chains and multicommodity flow. Combinatorics, probability and Computing, 1(4):351–370, 1992.
  32. Distributed subgradient methods for multi-agent optimization. IEEE Transactions on Automatic Control, 54(1):48–61, 2009.
  33. Dual averaging for distributed optimization: Convergence analysis and network scaling. IEEE Transactions on Automatic control, 57(3):592–606, 2011.
  34. Fast distributed gradient methods. IEEE Transactions on Automatic Control, 59(5):1131–1146, 2014.
  35. Nancy A Lynch. Distributed algorithms. Elsevier, 1996.
  36. Helge Tverberg. A generalization of radon’s theorem. Journal of the London Mathematical Society, 1(1):123–128, 1966.
  37. John R Reay. An extension of radon’s theorem. Illinois Journal of Mathematics, 12(2):184–189, 1968.
  38. Nitin H Vaidya. Iterative byzantine vector consensus in incomplete graphs. In Distributed Computing and Networking: 15th International Conference, ICDCN 2014, Coimbatore, India, January 4-7, 2014. Proceedings 15, pages 14–28. Springer, 2014.
  39. Brief announcement: Relaxed byzantine vector consensus. In Proceedings of the 28th ACM Symposium on Parallelism in Algorithms and Architectures, pages 401–403, 2016.
  40. Fault-tolerant rendezvous of multirobot systems. IEEE transactions on robotics, 33(3):565–582, 2017.
  41. Interplay between resilience and accuracy in resilient vector consensus in multi-agent networks. In 2020 59th IEEE Conference on Decision and Control (CDC), pages 3127–3132. IEEE, 2020.
  42. A “safe kernel” approach for resilient multi-dimensional consensus. IFAC-PapersOnLine, 53(2):2507–2512, 2020a.
  43. A survey of graph-theoretic approaches for analyzing the resilience of networked control systems. arXiv preprint arXiv:2205.12498, 2022.
  44. The condition number of a function relative to a set. Mathematical Programming, 188:255–294, 2021.
  45. Yurii Nesterov. Introductory lectures on convex optimization: A basic course, volume 87. Springer Science & Business Media, 2003.
  46. Formations for resilient robot teams. IEEE Robotics and Automation Letters, 2(2):841–848, 2017.
  47. Resilient consensus for time-varying networks of dynamic agents. In 2017 American control conference (ACC), pages 252–258. IEEE, 2017.
  48. Resilient distributed vector consensus using centerpoint. Automatica, 136:110046, 2022.
  49. On the set of possible minimizers of a sum of known and unknown functions. In 2020 American Control Conference (ACC), pages 106–111. IEEE, 2020.
  50. The minimizer of the sum of two strongly convex functions. arXiv preprint arXiv:2305.13134, 2023b.
  51. Resilient vector consensus: An event-based approach. In 2020 IEEE 16th International Conference on Control & Automation (ICCA), pages 889–894. IEEE, 2020b.
  52. An easy path to convex analysis and applications. Synthesis Lectures on Mathematics and Statistics, 6(2):1–218, 2013.
  53. Angles, triangle inequalities, correlation matrices and metric-preserving and subadditive functions. Linear Algebra and its Applications, 491:15–29, 2016.
Citations (4)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now