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

Social Opinion Formation and Decision Making Under Communication Trends (2203.02466v3)

Published 4 Mar 2022 in eess.SP, cs.MA, and cs.SI

Abstract: This work studies the learning process over social networks under partial and random information sharing. In traditional social learning models, agents exchange full belief information with each other while trying to infer the true state of nature. We study the case where agents share information about only one hypothesis, namely, the trending topic, which can be randomly changing at every iteration. We show that agents can learn the true hypothesis even if they do not discuss it, at rates comparable to traditional social learning. We also show that using one's own belief as a prior for estimating the neighbors' non-transmitted beliefs might create opinion clusters that prevent learning with full confidence. This phenomenon occurs when a single hypothesis corresponding to the truth is exchanged exclusively during all times. Such a practice, however, avoids the complete rejection of the truth under any information exchange procedure -- something that could happen if priors were uniform.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (59)
  1. C. P. Chamley, Rational Herds: Economic Models of Social Learning, Cambridge University Press, 2003.
  2. P. M. Djurić and Y. Wang, “Distributed Bayesian learning in multiagent systems: Improving our understanding of its capabilities and limitations,” IEEE Signal Processing Magazine, vol. 29, no. 2, pp. 65–76, 2012.
  3. “Models for the diffusion of beliefs in social networks: An overview,” IEEE Signal Processing Magazine, vol. 30, no. 3, pp. 16–29, 2013.
  4. V. Krishnamurthy and H. V. Poor, “Social learning and Bayesian games in multiagent signal processing: how do local and global decision makers interact?,” IEEE Signal Processing Magazine, vol. 30, no. 3, pp. 43–57, 2013.
  5. E. Mossel and O. Tamuz, “Opinion exchange dynamics,” Probability Surveys, vol. 14, pp. 155–204, 2017.
  6. “Learning from heterogeneous data based on social interactions over graphs,” IEEE Transactions on Information Theory, vol. 69, no. 5, pp. 3347–3371, 2023.
  7. “Non-Bayesian social learning,” Games and Economic Behavior, vol. 76, no. 1, pp. 210–225, 2012.
  8. X. Zhao and A. H. Sayed, “Learning over social networks via diffusion adaptation,” in Proc. Asilomar Conference on Signals, Systems and Computers, 2012, pp. 709–713.
  9. “Fast convergence rates for distributed non-Bayesian learning,” IEEE Transactions on Automatic Control, vol. 62, no. 11, pp. 5538–5553, 2017.
  10. “Social learning and distributed hypothesis testing,” IEEE Transactions on Information Theory, vol. 64, no. 9, pp. 6161–6179, 2018.
  11. “Non-Bayesian social learning on random digraphs with aperiodically varying network connectivity,” IEEE Transactions on Control of Network Systems, vol. 9, no. 3, pp. 1202–1214, 2022.
  12. “Bayesian learning in social networks,” The Review of Economic Studies, vol. 78, no. 4, pp. 1201–1236, 2011.
  13. “Bayesian decision making in groups is hard,” Operations Research, vol. 69, no. 2, pp. 632–654, 2021.
  14. H. A. Simon, “Bounded rationality,” in Utility and Probability, pp. 15–18. 1990.
  15. J. Conlisk, “Why bounded rationality?,” Journal of Economic Literature, vol. 34, no. 2, pp. 669–700, 1996.
  16. M. H. DeGroot, “Reaching a consensus,” Journal of the American Statistical Association, vol. 69, no. 345, pp. 118–121, 1974.
  17. A. H. Sayed, “Adaptation, learning, and optimization over networks,” Foundations and Trends in Machine Learning, vol. 7, no. 4-5, pp. 311–801, July 2014.
  18. “Partial information sharing over social learning networks,” IEEE Transactions on Information Theory, vol. 69, no. 3, pp. 2033–2058, 2023.
  19. “Social learning with sparse belief samples,” in Proc. IEEE CDC, 2020, pp. 1792–1797.
  20. “Event-triggered distributed inference,” in Proc. IEEE CDC, 2020, pp. 6228–6233.
  21. “Hypothesis assignment and partial likelihood averaging for cooperative estimation,” in Proc. IEEE CDC, 2019, pp. 7850–7856.
  22. “Social learning under randomized collaborations,” in Proc. IEEE ISIT, 2022, pp. 115–120.
  23. “Communication-efficient distributed cooperative learning with compressed beliefs,” IEEE Transactions on Control of Network Systems, vol. 9, no. 3, pp. 1215–1226, 2022.
  24. “Distributed inference with sparse and quantized communication,” IEEE Transactions on Signal Processing, vol. 69, pp. 3906–3921, 2021.
  25. “Memory-aware social learning under partial information sharing,” IEEE Transactions on Signal Processing, vol. 71, pp. 2833–2848, 2023.
  26. “Opinion fluctuations and disagreement in social networks,” Mathematics of Operations Research, vol. 38, no. 1, pp. 1–27, 2013.
  27. “Binary opinion dynamics with stubborn agents,” ACM Trans. Econ. Comput., vol. 1, no. 4, pp. 1–30, 2013.
  28. S. D. Lena, “Non-Bayesian social learning and the spread of misinformation in networks,” Working Papers 2019:09, Department of Economics, University of Venice Ca’ Foscari, 2019, available at SSRN: https://ssrn.com/abstract=3355245.
  29. D. Vial and V. Subramanian, “Local non-Bayesian social learning with stubborn agents,” IEEE Transactions on Control of Network Systems, vol. 9, no. 3, pp. 1178–1188, 2022.
  30. “Adaptive social learning,” IEEE Transactions on Information Theory, vol. 67, no. 9, pp. 6053–6081, 2021.
  31. “Distributed Bayesian learning of dynamic states,” arXiv:2212.02565, Dec. 2022.
  32. “On Krause’s multi-agent consensus model with state-dependent connectivity,” IEEE Transactions on Automatic Control, vol. 54, no. 11, pp. 2586–2597, 2009.
  33. “A model of online misinformation,” Working Paper 28884, National Bureau of Economic Research, June 2021.
  34. 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.
  35. A. H. Sayed, “Adaptive networks,” Proc. IEEE, vol. 102, no. 4, pp. 460–497, 2014.
  36. “Gossip algorithms for distributed signal processing,” Proc. IEEE, vol. 98, no. 11, pp. 1847–1864, 2010.
  37. A. H. Sayed, Inference and Learning from Data, Cambridge University Press, 2022, 3 vols.
  38. “Asynchronous decentralized optimization in heterogeneous systems,” in Proc. IEEE CDC, 2014, pp. 1125–1130.
  39. X. Zhao and A. H. Sayed, “Asynchronous adaptation and learning over networks—part i: Modeling and stability analysis,” IEEE Transactions on Signal Processing, vol. 63, no. 4, pp. 811–826, 2015.
  40. X. Zhao and A. H. Sayed, “Asynchronous adaptation and learning over networks—part ii: Performance analysis,” IEEE Transactions on Signal Processing, vol. 63, no. 4, pp. 827–842, 2015.
  41. X. Zhao and A. H. Sayed, “Asynchronous adaptation and learning over networks—part iii: Comparison analysis,” IEEE Transactions on Signal Processing, vol. 63, no. 4, pp. 843–858, 2015.
  42. “Asynchronous decentralized parallel stochastic gradient descent,” in Proc. International Conference on Machine Learning, 10–15 Jul 2018, vol. 80 of Proceedings of Machine Learning Research, pp. 3043–3052.
  43. “Asynchronous saddle point algorithm for stochastic optimization in heterogeneous networks,” IEEE Transactions on Signal Processing, vol. 67, no. 7, pp. 1742–1757, 2019.
  44. X. Cao and T. Başar, “Decentralized multi-agent stochastic optimization with pairwise constraints and quantized communications,” IEEE Transactions on Signal Processing, vol. 68, pp. 3296–3311, 2020.
  45. “Quantization of distributed data for learning,” IEEE Journal on Selected Areas in Information Theory, vol. 2, no. 3, pp. 987–1001, 2021.
  46. M. Ghassemi and A. D. Sarwate, “Distributed proportional stochastic coordinate descent with social sampling,” in Proc. Annual Allerton Conference on Communication, Control, and Computing, 2015, pp. 17–24.
  47. “Coordinate-descent diffusion learning by networked agents,” IEEE Transactions on Signal Processing, vol. 66, no. 2, pp. 352–367, 2017.
  48. “Performance of social machine learning under limited data,” in Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes Island, Greece, 2023, pp. 1–5.
  49. “Optimal distributed stochastic mirror descent for strongly convex optimization,” Automatica, vol. 90, pp. 196–203, 2018.
  50. “A tutorial on distributed (non-Bayesian) learning: Problem, algorithms and results,” in Proc. IEEE CDC, 2016, pp. 6795–6801.
  51. “Fusion of probability density functions,” Proc. IEEE, vol. 110, no. 4, pp. 404–453, 2022.
  52. “Second-order statistics analysis and comparison between arithmetic and geometric average fusion: Application to multi-sensor target tracking,” Information Fusion, vol. 51, pp. 233–243, 2019.
  53. “On the arithmetic and geometric fusion of beliefs for distributed inference,” IEEE Transactions on Automatic Control, pp. 1–16, 2023.
  54. “Nonasymptotic concentration rates in cooperative learning—part ii: Inference on compact hypothesis sets,” IEEE Transactions on Control of Network Systems, vol. 9, no. 3, pp. 1141–1153, 2022.
  55. “Distributed parameter estimation in sensor networks: Nonlinear observation models and imperfect communication,” IEEE Transactions on Information Theory, vol. 58, no. 6, pp. 3575–3605, 2012.
  56. K. Dedecius and P. M. Djurić, “Sequential estimation and diffusion of information over networks: A Bayesian approach with exponential family of distributions,” IEEE Transactions on Signal Processing, vol. 65, no. 7, pp. 1795–1809, 2017.
  57. Matrix Analysis, Cambridge University Press, 2012.
  58. D. Williams, Probability with Martingales, Cambridge University Press, 1991.
  59. E. Cesàro, “Sur la convergence des séries,” Nouvelles Annales de Mathématiques: Journal des Candidats aux Écoles Polytechnique et Normale, vol. 7, pp. 49–59, 1888.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (3)
  1. Mert Kayaalp (15 papers)
  2. Virginia Bordignon (19 papers)
  3. Ali H. Sayed (151 papers)
Citations (2)
View on Semantic Scholar

Summary

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

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