Papers
Topics
Authors
Recent
Assistant
AI Research Assistant
Well-researched responses based on relevant abstracts and paper content.
Custom Instructions Pro
Preferences or requirements that you'd like Emergent Mind to consider when generating responses.
Gemini 2.5 Flash
Gemini 2.5 Flash 147 tok/s
Gemini 2.5 Pro 50 tok/s Pro
GPT-5 Medium 25 tok/s Pro
GPT-5 High 20 tok/s Pro
GPT-4o 90 tok/s Pro
Kimi K2 192 tok/s Pro
GPT OSS 120B 424 tok/s Pro
Claude Sonnet 4.5 39 tok/s Pro
2000 character limit reached

Decentralized Multi-Task Online Convex Optimization Under Random Link Failures (2401.02011v1)

Published 4 Jan 2024 in cs.LG and math.OC

Abstract: Decentralized optimization methods often entail information exchange between neighbors. Transmission failures can happen due to network congestion, hardware/software issues, communication outage, and other factors. In this paper, we investigate the random link failure problem in decentralized multi-task online convex optimization, where agents have individual decisions that are coupled with each other via pairwise constraints. Although widely used in constrained optimization, conventional saddle-point algorithms are not directly applicable here because of random packet dropping. To address this issue, we develop a robust decentralized saddle-point algorithm against random link failures with heterogeneous probabilities by replacing the missing decisions of neighbors with their latest received values. Then, by judiciously bounding the accumulated deviation stemming from this replacement, we first establish that our algorithm achieves $\mathcal{O}(\sqrt{T})$ regret and $\mathcal{O}(T\frac{3}{4})$ constraint violations for the full information scenario, where the complete information on the local cost function is revealed to each agent at the end of each time slot. These two bounds match, in order sense, the performance bounds of algorithms with perfect communications. Further, we extend our algorithm and analysis to the two-point bandit feedback scenario, where only the values of the local cost function at two random points are disclosed to each agent sequentially. Performance bounds of the same orders as the full information case are derived. Finally, we corroborate the efficacy of the proposed algorithms and the analytical results through numerical simulations.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (37)
  1. E. Hazan et al., “Introduction to online convex optimization,” Found. Trends Opt., vol. 2, no. 3-4, pp. 157–325, Aug. 2016.
  2. X. Li, L. Xie, and N. Li, “A survey of decentralized online learning,” 2022. [Online]. Available: https://arxiv.org/abs/2205.00473
  3. Y. Arjevani, O. Shamir, and N. Srebro, “A tight convergence analysis for stochastic gradient descent with delayed updates,” in Algorithmic Learning Theory.   PMLR, 2020, pp. 111–132.
  4. X. Cao and T. Başar, “Decentralized online convex optimization based on signs of relative states,” Automatic., vol. 129, p. 109676, Jul. 2021.
  5. S. Shalev-Shwartz et al., “Online learning and online convex optimization,” Found. Trends Mach. Learn., vol. 4, no. 2, pp. 107–194, Mar. 2012.
  6. W. Yan, X. Yuan, Z.-Q. He, and X. Kuai, “Passive beamforming and information transfer design for reconfigurable intelligent surfaces aided multiuser mimo systems,” IEEE J. Sel. Areas Commun., vol. 38, no. 8, pp. 1793–1808, Aug. 2020.
  7. Y. Wenjing and X. Cao, “Zero-regret performative prediction under inequality constraints,” in Thirty-seventh Conference on Neural Information Processing Systems, 2023.
  8. A. Koppel, F. Y. Jakubiec, and A. Ribeiro, “A saddle point algorithm for networked online convex optimization,” IEEE Trans. Signal Process., vol. 63, no. 19, pp. 5149–5164, Oct. 2015.
  9. W. Yan, X. Yuan, and X. Kuai, “Passive beamforming and information transfer via large intelligent surface,” IEEE Wirel. Commun. Let., vol. 9, no. 4, pp. 533–537, Apr. 2019.
  10. J. Postel, “Transmission control protocol,” Tech. Rep., 1981.
  11. ——, “User datagram protocol,” Tech. Rep., 1980.
  12. Y. Hatano and M. Mesbahi, “Agreement over random networks,” IEEE Trans. Aut. Contr., vol. 50, no. 11, pp. 1867–1872, Nov. 2005.
  13. S. Boyd, A. Ghosh, B. Prabhakar, and D. Shah, “Randomized gossip algorithms,” IEEE Trans. Inf. Theory, vol. 52, no. 6, pp. 2508–2530, Jun. 2006.
  14. A. Nedic and A. Ozdaglar, “Distributed subgradient methods for multi-agent optimization,” IEEE Trans. Aut. Contr., vol. 54, no. 1, pp. 48–61, Jan. 2009.
  15. V. S. Mai and E. H. Abed, “Distributed optimization over weighted directed graphs using row stochastic matrix,” in Proc. 2016 Amer. Control Conf. (ACC).   Boston, MA, USA, Jul. 2016, pp. 7165–7170.
  16. C. Xi, V. S. Mai et al., “Linear convergence in optimization over directed graphs with row-stochastic matrices,” IEEE Trans. Aut. Contr., vol. 63, no. 10, pp. 3558–3565, Oct. 2018.
  17. H. Ye, L. Liang, and G. Y. Li, “Decentralized federated learning with unreliable communications,” IEEE J. Sel. Top. Signal Process., vol. 16, no. 3, pp. 487–500, Apr. 2022.
  18. S. Bhattacharya and V. Kumar, “Distributed optimization with pairwise constraints and its application to multi-robot path planning,” Rob.: Sci. Syst. VI, vol. 177, 2011.
  19. B. Bhattarai, G. Sharma, and F. Jurie, “Cp-mtML: Coupled projection multi-task metric learning for large scale face retrieval,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2016, pp. 4226–4235.
  20. A. Koppel, B. M. Sadler, and A. Ribeiro, “Proximity without consensus in online multiagent optimization,” IEEE Trans. Signal Process., vol. 65, no. 12, pp. 3062–3077, Jun. 2017.
  21. A. S. Bedi, A. Koppel, and K. Rajawat, “Asynchronous online learning in multi-agent systems with proximity constraints,” IEEE Trans. Sig. Inf. Process. Net., vol. 5, no. 3, pp. 479–494, Sept. 2019.
  22. F. Ho, R. Geraldes, A. Gonçalves, B. Rigault, B. Sportich, D. Kubo, M. Cavazza, and H. Prendinger, “Decentralized multi-agent path finding for UAV traffic management,” IEEE Trans. Int. Transp. Syst., vol. 23, no. 2, pp. 997–1008, Feb. 2020.
  23. P. Mirowski, T. K. Ho, S. Yi, and M. MacDonald, “SignalSLAM: Simultaneous localization and mapping with mixed WiFi, Bluetooth, LTE and magnetic signals,” in Int. Conf. Indoor Posit. Indoor Navig., 2013, pp. 1–10.
  24. J. Salvado, M. Mansouri, and F. Pecora, “DiMOpt: a distributed multi-robot trajectory optimization algorithm,” in 2022 IEEE/RSJ Int. Conf. Int. Rob. Syst. (IROS), 2022, pp. 10 110–10 117.
  25. H. Fouad and G. Beltrame, “Energy autonomy for resource-constrained multi robot missions,” in 2020 IEEE/RSJ Int. Conf. Int. Rob. Syst. (IROS).   IEEE, 2020, pp. 7006–7013.
  26. A. Nedic, A. Olshevsky, and W. Shi, “Achieving geometric convergence for distributed optimization over time-varying graphs,” SIAM J. Optim., vol. 27, no. 4, pp. 2597–2633, 2017.
  27. Z. Chen, L. Cai, and C. Zhao, “Convergence time of average consensus with heterogeneous random link failures,” Automatica, vol. 127, p. 109496, 2021.
  28. X. Cao and T. Başar, “Decentralized multi-agent stochastic optimization with pairwise constraints and quantized communications,” IEEE Trans. Signal Process., vol. 68, pp. 3296–3311, 2020.
  29. A. D. Flaxman, A. T. Kalai, A. T. Kalai, and H. B. McMahan, “Online convex optimization in the bandit setting: gradient descent without a gradient,” in Proc. 16th Annu. ACM-SIAM Symp. Discrete Algorithms, 2005, pp. 385–394.
  30. A. S. Bedi, A. Koppel, and K. Rajawat, “Asynchronous saddle point algorithm for stochastic optimization in heterogeneous networks,” IEEE Trans. Sig. Process., vol. 67, no. 7, pp. 1742–1757, Apri 2019.
  31. Q. Sun, G. Zhu, C. Shen, X. Li, and Z. Zhong, “Joint beamforming design and time allocation for wireless powered communication networks,” IEEE Commun. Lett., vol. 18, no. 10, pp. 1783–1786, Oct 2014.
  32. Y. Wang, L. Chen, J. Zhou, T. Li, and Y. Yu, “Pairwise constraints-based semi-supervised fuzzy clustering with multi-manifold regularization,” Information Sciences, vol. 638, p. 118994, 2023.
  33. X. Cao and T. Başar, “Decentralized online convex optimization with event-triggered communications,” IEEE Trans. Signal Process., vol. 69, pp. 284–299, 2021.
  34. D. Yuan, D. W. Ho, and G.-P. Jiang, “An adaptive primal-dual subgradient algorithm for online distributed constrained optimization,” IEEE trans. cybern., vol. 48, no. 11, pp. 3045–3055, Nov. 2017.
  35. N. Singh, X. Cao, S. Diggavi, and T. Başar, “Decentralized multi-task stochastic optimization with compressed communications,” Automatica, vol. 159, p. 111363, 2024.
  36. Y. Chen, L. Tai, K. Sun, and M. Li, “Monopair: Monocular 3d object detection using pairwise spatial relationships,” in Proceedings of the IEEE/CVF Conf. Computer Vis. Pat. Recog., 2020, pp. 12 093–12 102.
  37. M. Liu and D. Zhang, “Pairwise constraint-guided sparse learning for feature selection,” IEEE trans. cybern., vol. 46, no. 1, pp. 298–310, 2015.
Citations (1)
View on Semantic Scholar

Summary

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

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

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now
Lightbulb Streamline Icon: https://streamlinehq.com

Continue Learning

We haven't generated follow-up questions for this paper yet.

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

Authors (2)

  1. Wenjing Yan
  2. Xuanyu Cao
List To Do Tasks Checklist Streamline Icon: https://streamlinehq.com

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets

This paper has been mentioned in 1 tweet and received 0 likes.

Upgrade to Pro to view all of the tweets about this paper:

Start a free 7-day Pro trial