×

A general analysis of boundedly rational learning in social networks. (English) Zbl 1475.91259

Summary: We analyze boundedly rational learning in social networks within binary action environments. We establish how learning outcomes depend on the environment (i.e., informational structure, utility function), the axioms imposed on the updating behavior, and the network structure. In particular, we provide a normative foundation for quasi-Bayesian updating, where a quasi-Bayesian agent treats others’ actions as if they were based only on their private signal. Quasi-Bayesian updating induces learning (i.e., convergence to the optimal action for every agent in every connected network) only in highly asymmetric environments. In all other environments, learning fails in networks with a diameter larger than 4. Finally, we consider a richer class of updating behavior that allows for nonstationarity and differential treatment of neighbors’ actions depending on their position in the network. We show that within this class there exist updating systems that induce learning for most networks.

MSC:

91D30 Social networks; opinion dynamics
91D15 Social learning
Full Text: DOI

References:

[1] Acemoglu, Daron, Munther A.Dahleh, IlanLobel, and AsumanOzdaglar (2011), “Bayesian learning in social networks.” Review of Economic Studies, 78, 1201-1236. · Zbl 1274.91354
[2] Alatas, Vivi, AbhijitBanerjee, Arun G.Chandrasekhar, RemaHanna, and Benjamin A.Olken (2016), “Network structure and the aggregation of information: Theory and evidence from Indonesia.” American Economic Review, 106, 1663-1704.
[3] Arieli, Itai, YakovBabichenko, and ManuelMueller‐Frank (2020), “Naive learning through probability matching.” Unpublished paper, SSRN 3338015.
[4] Arieli, Itai and ManuelMueller‐Frank (2017), “Inferring beliefs from actions.” Games and Economic Behavior, 102, 455-461. · Zbl 1409.91082
[5] Arieli, Itai and ManuelMueller‐Frank (2019), “Multi‐dimensional social learning.” Review of Economic Studies, 86, 913-940. · Zbl 1479.91272
[6] Bala, Venkatesh and SanjeevGoyal (1998), “Learning from neighbours.” Review of Economic Studies, 65, 595-621. · Zbl 0910.90103
[7] Banerjee, Abhijit V. (1992), “A simple model of herd behavior.” Quarterly Journal of Economics, 107, 797-817.
[8] Banerjee, Abhijit V., EmilyBreza, Arun G.Chandrasekhar, and MarkusMobius (2019), “Naive learning with uninformed agents.” Working paper, No. 25497.
[9] Banerjee, Abhijit V., Arun G.Chandrasekhar, EstherDuflo, and Matthew O.Jackson (2013), “The diffusion of microfinance.” Science, 341.
[10] Bikhchandani, Sushil, DavidHirshleifer, and IvoWelch (1992), “A theory of fads, fashion, custom, and cultural change as information cascades.” Journal of Political Economy, 100, 992-1026.
[11] Bohren, J. Aislinn (2016), “Informational herding with model misspecification.” Journal of Economic Theory, 163, 222-247. · Zbl 1369.91156
[12] Breza, Emily, ArunChandrasekhar, and AlirezaTahbaz‐Salehi (2018), “Seeing the forest for the trees? An investigation of network knowledge.” Working paper, NBER Working Paper No. w24359.
[13] Camerer, Colin, Teck‐HuaHo, and Juin‐KuanChong (2004), “A cognitive hierarchy model of games.” Quarterly Journal of Economics, 119, 861-898. · Zbl 1074.91503
[14] Casciaro, Tiziana (1998), “Seeing things clearly: Social structure, personality, and accuracy in social network perception.” Social Networks, 20, 331-351.
[15] Chandrasekhar, Arun G., HoracioLarreguy, and Juan PabloXandri (2020), “Testing models of social learning on networks: Evidence from two experiments.” Econometrica, 88, 1-32. · Zbl 1466.91224
[16] Crawford, Vincent P., Miguel A.Costa‐Gomes, and NagoreIriberri (2013), “Structural models of nonequilibrium strategic thinking: Theory, evidence, and applications.” Journal of Economic Literature, 51, 5-62.
[17] Dasaratha, Krishna and KevinHe (2020), “Network structure and naive sequential learning.” Theoretical Economics, 15, 415-444. · Zbl 1466.91225
[18] De Marzo, Peter, DimitriVayanos, and JeffreyZwiebel (2003), “Persuasion bias, social influence, and unidimensional opinions.” Quarterley Journal of Economics, 118, 909-968. · Zbl 1069.91093
[19] DeGroot, Morris H. (1974), “Reaching a consensus.” Journal of the American Statistical Association, 69, 118-121. · Zbl 0282.92011
[20] Enke, Benjamin and FlorianZimmerman (2019), “Correlation neglect in belief formation.” Review of Economics Studies, 86, 313-332. · Zbl 1409.91088
[21] Eyster, Erik and MatthewRabin (2010), “Naive herding in rich‐information settings.” American Economic Journal: Microeconomics, 2, 221-243.
[22] Eyster, Erik, MatthewRabin, and GeorgWeizsäcker (2015), “An experiment on social mislearning.” Unpublished paper, SSRN 2704746.
[23] Feldman, Michal, NicoleImmorlica, BrendanLucier, and S. MatthewWeinberg (2014), “Reaching consensus via non‐Bayesian asynchronous learning in social networks.” Unpublished paper, arxiv:1408.5192.
[24] Gagnon‐Bartsch, Tristan and MatthewRabin (2016), “Naive social learning, mislearning, and unlearning.” Unpublished paper, Department of Economics and Business School, Harvard University.
[25] Gale, Douglas M. and ShacharKariv (2003), “Bayesian learning in social networks.” Games and Economic Behavior, 45, 329-346. · Zbl 1069.91094
[26] Glaeser, Edward and Cass R.Sunstein (2009), Extremism and Social Learning, volume 1, 263-324.
[27] Goles, Eric and J.Olivos (1980), “Periodic behavior of generalized threshold functions.” Discrete Mathematics, 30, 187-189. · Zbl 0444.94038
[28] Golub, Benjamin and MatthewJackson (2012), “How homophily affects the speed of learning and best‐response dynamics.” Quarterly Journal ofEconomics, 127, 1287-1338. · Zbl 1400.91465
[29] Golub, Benjamin and Matthew O.Jackson (2010), “Naïve learning in social networks and the wisdom of crowds.” American Economic Journal: Microeconomics, 2, 112-149.
[30] Hazla, Jan, AliJadbabaie, ElchananMossel, and M. AminRahimian (2018), “Reasoning in Bayesian opinion exchange networks is PSPACE‐hard.” Unpublished paper, arXiv:1809.01077.
[31] Jadbabaie, Ali, PooyaMolavi, AlvaroSandroni, and AlirezaTahbaz‐Salehi (2012), “Non‐Bayesian social learning.” Games and Economic Behavior, 76, 210-225. · Zbl 1274.91359
[32] Krackhardt, David (1990), “Assessing the political landscape: Structure, cognition, and power in organizations.” Administrative Science Quarterly, 35, 342-369.
[33] Kübler, Dorothea and GeorgWeizsäcker (2004), “Limited depth of reasoning and failure of cascade formation in the laboratory.” Review of Economic Studies, 71, 425-441. · Zbl 1096.91008
[34] Lee, In Ho (1993), “On the convergence of informational cascades.” Journal of Economic Theory, 61, 395-411. · Zbl 0796.90012
[35] Lobel, Ilan and EvanSadler (2015), “Information diffusion in networks through social learning.” Theoretical Economics, 10, 807-851. · Zbl 1395.91375
[36] March, Christoph and AnthonyZiegelmeyer (2018), “Excessive herding in the laboratory: The role of intuitive judgments.” Unpublished paper, SSRN 3140365.
[37] Mobius, Markus, TuanPhan, and AdamSzeidl (2015), “Treasure hunt: Social learning in the field.”
[38] Molavi, Pooya, AlirezaTahbaz‐Salehi, and AliJadbabaie (2018), “A theory of non‐Bayesian social learning.” Econometrica, 86, 445-490. · Zbl 1419.91560
[39] Morris, Stephen (2000), “Contagion.” Review of Economic Studies, 67, 57-78. · Zbl 0960.91016
[40] Mossel, Elchanan, ManuelMueller‐Frank, AllanSly, and OmerTamuz (2020), “Social learning equilibria.” Econometrica, 88, 1235-1267. · Zbl 1466.91229
[41] Mossel, Elchanan, AllanSly, and OmerTamuz (2015), “Strategic learning and the topology of social networks.” Econometrica, 83, 1755-1794. · Zbl 1419.91561
[42] Mueller‐Frank, Manuel (2013), “A general framework for rational learning in social networks.” Theoretical Economics, 8, 1-40. · Zbl 1395.91377
[43] Mueller‐Frank, Manuel (2014), “Does one Bayesian make a difference?” Journal of Economic Theory, 154, 423-452. · Zbl 1309.91114
[44] Mueller‐Frank, Manuel and ClaudiaNeri (2015), “A general model of boundedly rational observational learning: Theory and evidence.” Unpublished paper, SSRN 2566210.
[45] Nagel, Rosemarie C. (1995), “Unraveling in guessing games: An experimental study.” American Economic Review, 85, 1313-1326.
[46] Rosenberg, Dinah, EilonSolan, and NicolasVieille (2009), “Information externalities and emergence of consensus,”.” Games and Economic Behavior, 66, 979-994. · Zbl 1165.91327
[47] Smith, Lones and PeterSørensen (2000), “Pathological outcomes of observational learning.” Econometrica, 68, 371-398. · Zbl 1023.91510
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.