Papers
Topics
Authors
Recent
Search
2000 character limit reached

Distributed Optimization with Finite Bit Adaptive Quantization for Efficient Communication and Precision Enhancement

Published 9 Sep 2024 in eess.SY, cs.SY, and math.OC | (2409.05418v2)

Abstract: In realistic distributed optimization scenarios, individual nodes possess only partial information and communicate over bandwidth constrained channels. For this reason, the development of efficient distributed algorithms is essential. In our paper we addresses the challenge of unconstrained distributed optimization. In our scenario each node's local function exhibits strong convexity with Lipschitz continuous gradients. The exchange of information between nodes occurs through $3$-bit bandwidth-limited channels (i.e., nodes exchange messages represented by a only $3$-bits). Our proposed algorithm respects the network's bandwidth constraints by leveraging zoom-in and zoom-out operations to adjust quantizer parameters dynamically. We show that during our algorithm's operation nodes are able to converge to the exact optimal solution. Furthermore, we show that our algorithm achieves a linear convergence rate to the optimal solution. We conclude the paper with simulations that highlight our algorithm's unique characteristics.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (27)
  1. A. Nedich, “Distributed gradient methods for convex machine learning problems in networks: Distributed optimization,” IEEE Signal Processing Magazine, vol. 37, no. 3, pp. 92–101, 2020.
  2. G. S. Seyboth, D. V. Dimarogonas, and K. H. Johansson, “Event-based broadcasting for multi-agent average consensus,” Automatica, vol. 49, no. 1, pp. 245–252, 2013.
  3. S. U. Stich, J. B. Cordonnier, and M. Jaggi, “Sparsified SGD with memory,” in Advances in Neural Information Processing Systems, vol. 31.   Curran Associates, Inc., 2018, pp. 4447–4458.
  4. A. Nedić and J. Liu, “Distributed optimization for control,” Annual Review of Control, Robotics, and Autonomous Systems, vol. 1, pp. 77–103, 2018.
  5. A. Nedic and A. Ozdaglar, “Distributed subgradient methods for multi-agent optimization,” IEEE Transactions on Automatic Control, vol. 54, no. 1, pp. 48–61, 2009.
  6. R. Xin and U. A. Khan, “A linear algorithm for optimization over directed graphs with geometric convergence,” IEEE Control Systems Letters, vol. 2, no. 3, pp. 315–320, 2018.
  7. V. Khatana, G. Saraswat, S. Patel, and M. V. Salapaka, “Gradient-consensus method for distributed optimization in directed multi-agent networks,” in 2020 American Control Conference (ACC), 2020, pp. 4689–4694.
  8. T. Qin, S. R. Etesami, and C. A. Uribe, “Communication-efficient decentralized local SGD over undirected networks,” in 2021 60th IEEE Conference on Decision and Control (CDC), 2021, pp. 3361–3366.
  9. P. Yi and Y. Hong, “Quantized subgradient algorithm and data-rate analysis for distributed optimization,” IEEE Transactions on Control of Network Systems, vol. 1, no. 4, pp. 380–392, 2014.
  10. C. Huang, H. Li, D. Xia, and L. Xiao, “Quantized subgradient algorithm with limited bandwidth communications for solving distributed optimization over general directed multi-agent networks,” Neurocomputing, vol. 185, pp. 153–162, 2016.
  11. Y. Pu, M. N. Zeilinger, and C. N. Jones, “Quantization design for distributed optimization,” IEEE Transactions on Automatic Control, vol. 62, no. 5, pp. 2107–2120, 2017.
  12. H. Li, S. Liu, Y. C. Soh, and L. Xie, “Event-triggered communication and data rate constraint for distributed optimization of multiagent systems,” IEEE Transactions on Systems, Man, and Cybernetics: Systems, vol. 48, no. 11, pp. 1908–1919, 2018.
  13. T. T. Doan, S. T. Maguluri, and J. Romberg, “Fast convergence rates of distributed subgradient methods with adaptive quantization,” IEEE Transactions on Automatic Control, vol. 66, no. 5, pp. 2191–2205, 2021.
  14. S. Magnusson, H. Shokri-Ghadikolaei, and N. Li, “On maintaining linear convergence of distributed learning and optimization under limited communication,” IEEE Transactions on Signal Processing, vol. 68, pp. 6101–6116, 2020.
  15. D. Jhunjhunwala, A. Gadhikar, G. Joshi, and Y. C. Eldar, “Adaptive quantization of model updates for communication-efficient federated learning,” in ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021, pp. 3110–3114.
  16. Y. Kajiyama, N. Hayashi, and S. Takai, “Linear convergence of consensus-based quantized optimization for smooth and strongly convex cost functions,” IEEE Transactions on Automatic Control, vol. 66, no. 3, pp. 1254–1261, 2021.
  17. J. Liu, Z. Yu, and D. W. C. Ho, “Distributed constrained optimization with delayed subgradient information over time-varying network under adaptive quantization,” IEEE Transactions on Neural Networks and Learning Systems, pp. 1–14, 2022.
  18. A. Koloskova, S. Stich, and M. Jaggi, “Decentralized stochastic optimization and gossip algorithms with compressed communication,” in Proceedings of the 36th International Conference on Machine Learning, 2019, pp. 3478–3487.
  19. D. Basu, D. Data, C. Karakus, and S. Diggavi, “Qsparse-local-SGD: Distributed SGD with quantization, sparsification and local computations,” in Advances in Neural Information Processing Systems, vol. 32, 2019.
  20. B. Li, S. Cen, Y. Chen, and Y. Chi, “Communication-efficient distributed optimization in networks with gradient tracking and variance reduction,” in Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics, 2020, pp. 1662–1672.
  21. S. Horváth, D. Kovalev, K. Mishchenko, P. Richtárik, and S. Stich, “Stochastic distributed learning with gradient quantization and double-variance reduction,” Optimization Methods and Software, vol. 38, no. 1, pp. 91–106, 2023.
  22. A. I. Rikos, W. Jiang, T. Charalambous, and K. H. Johansson, “Distributed optimization with gradient descent and quantized communication,” IFAC-PapersOnLine, vol. 56, no. 2, pp. 5900–5906, 2023.
  23. ——, “Distributed optimization via gradient descent with event-triggered zooming over quantized communication,” in IEEE Conference on Decision and Control, 2023, pp. 6321–6327.
  24. J. Xu, S. Zhu, Y. C. Soh, and L. Xie, “Convergence of asynchronous distributed gradient methods over stochastic networks,” IEEE Transactions on Automatic Control, vol. 63, no. 2, pp. 434–448, 2018.
  25. G. Qu and N. Li, “Harnessing smoothness to accelerate distributed optimization,” IEEE Transactions on Control of Network Systems, vol. 5, no. 3, pp. 1245–1260, 2018.
  26. G. Oliva, R. Setola, and C. N. Hadjicostis, “Distributed finite-time calculation of node eccentricities, graph radius and graph diameter,” Systems & Control Letters, vol. 92, pp. 20–27, 2016.
  27. J. Cortés, “Distributed algorithms for reaching consensus on general functions,” Automatica, vol. 44, no. 3, pp. 726–737, March 2008.

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

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

Generate Now

Continue Learning

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

Generate Now

Collections

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

Sign Up