Bayesian Group Decisions: Algorithms and Complexity

We address the computations that Bayesian agents undertake to realize their optimal actions, as they repeatedly observe each other's actions, following an initial private observation. We use iterated eliminations of infeasible signals (IEIS) to model the thinking process as well as the calculations of a Bayesian agent in a group decision scenario. We show that IEIS runs in exponential time; however, when the group structure is a partially ordered set, the Bayesian calculations simplify and polynomial-time computation of the Bayesian recommendations is possible. We next shift attention to the case where agents reveal their beliefs (instead of actions) at every decision epoch. We analyze the computational complexity of the Bayesian belief formation in groups and show that it is NP-hard. We also investigate the factors underlying this computational complexity and show how belief calculations simplify in special network structures or cases with strong inherent symmetries. We finally give insights about the statistical efficiency (optimality) of the beliefs and its relations to computational efficiency.

[1]  Kumaraswamy Velupillai,et al.  Computable Economics: The Arne Ryde Memorial Lectures , 2000 .

[2]  A. Banerjee,et al.  A Simple Model of Herd Behavior , 1992 .

[3]  M. Rabin,et al.  Naïve Herding in Rich-Information Settings , 2010 .

[4]  Ehud Lehrer,et al.  Merging and learning , 1996 .

[5]  Venkat Chandrasekaran,et al.  Complexity of Inference in Graphical Models , 2008, UAI.

[6]  Scott Aaronson,et al.  The complexity of agreement , 2004, STOC '05.

[7]  Elchanan Mossel,et al.  Reasoning in Bayesian Opinion Exchange Networks Is PSPACE-Hard , 2018, COLT.

[8]  Lones Smith,et al.  Pathological Outcomes of Observational Learning , 2000 .

[9]  Matthew O. Jackson,et al.  Näıve Learning in Social Networks : Convergence , Influence , and the Wisdom of Crowds ∗ , 2007 .

[10]  Teofilo F. GONZALEZ,et al.  Clustering to Minimize the Maximum Intercluster Distance , 1985, Theor. Comput. Sci..

[11]  Causing Human Actions , 2010 .

[12]  Ilan Lobel,et al.  BAYESIAN LEARNING IN SOCIAL NETWORKS , 2008 .

[13]  Gregory F. Cooper,et al.  The Computational Complexity of Probabilistic Inference Using Bayesian Belief Networks , 1990, Artif. Intell..

[14]  S. Goyal,et al.  Learning from neighbours , 1998 .

[15]  Elchanan Mossel,et al.  Efficient Bayesian Learning in Social Networks with Gaussian Estimators , 2010, 2016 54th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[16]  Ali Jadbabaie,et al.  Bayesian Learning Without Recall , 2016, IEEE Transactions on Signal and Information Processing over Networks.

[17]  Michael I. Jordan,et al.  Loopy Belief Propagation for Approximate Inference: An Empirical Study , 1999, UAI.

[18]  J. Cave Learning to agree , 1983 .

[19]  Alejandro Ribeiro,et al.  Learning to Coordinate in Social Networks , 2014, Oper. Res..

[20]  Bauke Visser,et al.  Organizational Communication Structure and Performance , 2000 .

[21]  Ali Jadbabaie,et al.  A Theory of Non‐Bayesian Social Learning , 2018 .

[22]  Ali Jadbabaie,et al.  Non-Bayesian Social Learning , 2011, Games Econ. Behav..

[23]  J. Geanakoplos,et al.  We Can't Disagree Forever , 1982 .

[24]  John N. Tsitsiklis,et al.  On the complexity of decentralized decision making and detection problems , 1985 .

[25]  M. Rabin,et al.  Extensive Imitation is Irrational and Harmful , 2014 .

[26]  Elchanan Mossel,et al.  Asymptotic learning on Bayesian social networks , 2012, Probability Theory and Related Fields.

[27]  Vikram Krishnamurthy,et al.  Online Reputation and Polling Systems: Data Incest, Social Learning, and Revealed Preferences , 2014, IEEE Transactions on Computational Social Systems.

[28]  Yudong Chen,et al.  Statistical-Computational Tradeoffs in Planted Problems and Submatrix Localization with a Growing Number of Clusters and Submatrices , 2014, J. Mach. Learn. Res..

[29]  J. Stiglitz,et al.  The Architecture of Economic Systems: Hierarchies and Polyarchies , 1984 .

[30]  Richard M. Karp,et al.  Reducibility Among Combinatorial Problems , 1972, 50 Years of Integer Programming.

[31]  John N. Tsitsiklis,et al.  The Complexity of Markov Decision Processes , 1987, Math. Oper. Res..

[32]  Richard M. Karp,et al.  Reducibility among combinatorial problems" in complexity of computer computations , 1972 .

[33]  Elchanan Mossel,et al.  Strategic Learning and the Topology of Social Networks , 2012, ArXiv.

[34]  Sanjeev Arora,et al.  Computational Complexity: A Modern Approach , 2009 .

[35]  Manuel Mueller-Frank,et al.  A general framework for rational learning in social networks , 2011 .

[36]  Paul W. Goldberg,et al.  The complexity of computing a Nash equilibrium , 2006, STOC '06.

[37]  David S. Johnson,et al.  Computers and Intractability: A Guide to the Theory of NP-Completeness , 1978 .

[38]  Rohit Parikh,et al.  Communication, consensus, and knowledge , 1990 .

[39]  R. Radner,et al.  Team Decision Problems , 1962 .

[40]  Thorbjørn Knudsen,et al.  Design of Decision-Making Organizations , 2010, Manag. Sci..

[41]  Asuman E. Ozdaglar,et al.  Opinion Dynamics and Learning in Social Networks , 2010, Dyn. Games Appl..

[42]  R. Aumann Agreeing to disagree. , 1976, Nature cell biology.

[43]  J. Stiglitz,et al.  Committees, hierarchies and polyarchies , 1987 .

[44]  Subhash Khot,et al.  Pseudorandom Sets in Grassmann Graph Have Near-Perfect Expansion , 2018, 2018 IEEE 59th Annual Symposium on Foundations of Computer Science (FOCS).

[45]  R. Gibbons Incentives in Organizations , 1998 .

[46]  Elchanan Mossel,et al.  Making Consensus Tractable , 2010, TEAC.

[47]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[48]  Spyros Vassilakis,et al.  Accelerating New Product Development by Overcoming Complexity Constraints , 2002 .

[49]  Yashodhan Kanoria,et al.  Tractable Bayesian Social Learning on Trees , 2012, IEEE Journal on Selected Areas in Communications.

[50]  David J. Spiegelhalter,et al.  Probabilistic Networks and Expert Systems - Exact Computational Methods for Bayesian Networks , 1999, Information Science and Statistics.

[51]  Yannis M. Ioannides On the architecture of complex organizations , 1987 .

[52]  Felipe A. Csaszar,et al.  Organizational Decision Making: An Information Aggregation View , 2012, Manag. Sci..

[53]  Luca Trevisan Average-case Complexity , 2008, 2008 49th Annual IEEE Symposium on Foundations of Computer Science.

[54]  Ali Jadbabaie,et al.  Bayesian Heuristics for Group Decisions , 2016, ArXiv.

[55]  Quentin Berthet,et al.  Statistical and computational trade-offs in estimation of sparse principal components , 2014, 1408.5369.

[56]  M. Bacharach Some extensions of a claim of Aumann in an axiomatic model of knowledge , 1985 .

[57]  Elchanan Mossel,et al.  On the Speed of Social Learning , 2014, SSRN Electronic Journal.

[58]  Yashodhan Kanoria,et al.  Tractable Bayesian Social Learning on Trees , 2013, IEEE J. Sel. Areas Commun..

[59]  D. Blackwell,et al.  Merging of Opinions with Increasing Information , 1962 .

[60]  Pooya Molavi,et al.  Foundations of Non-Bayesian Social Learning , 2016 .

[61]  R. Radner,et al.  Economic theory of teams , 1972 .

[62]  Paul W. Goldberg,et al.  The Complexity of Computing a Nash Equilibrium , 2009, SIAM J. Comput..

[63]  Nicolas Vieille,et al.  Informational externalities and emergence of consensus , 2009, Games Econ. Behav..

[64]  S. Bikhchandani,et al.  Learning from the behavior of others : conformity, fads, and informational cascades , 1998 .

[65]  Krishna Dasaratha,et al.  Bayesian Social Learning in a Dynamic Environment , 2018, EC.

[66]  P. Bolton,et al.  The firm as a communication network , 1994 .

[67]  Joseph E. Stiglitz,et al.  Human Fallibility and Economic Organization , 1985 .

[68]  Felipe A. Csaszar,et al.  Organizational Decision Making: An Information Aggregation View , 2012 .

[69]  H PapadimitriouChristos,et al.  The complexity of computing a Nash equilibrium , 2009 .