When is social computation better than the sum of its parts?
Social computation, whether in the form of searches performed by swarms of agents or collective predictions of markets, often supplies remarkably good solutions to complex problems. In many examples, individuals trying to solve a problem locally can aggregate their information and work together to arrive at a superior global solution. This suggests that there may be general principles of information aggregation and coordination that can transcend particular applications. Here we show that the general structure of this problemcan be cast in terms of information theory and derive mathematical conditions that lead to optimal multi-agent searches. Specifically, we illustrate the problem in terms of local search algorithms for autonomous agents looking for the spatial location of a stochastic source. We explore the types of search problems, defined in terms of the statistical properties of the source and the nature of measurements at each agent, for which coordination among multiple searchers yields an advantage beyond that gained by having the same number of independent searchers. We show that effective coordination corresponds to synergy and that ineffective coordination corresponds to independence as defined using information theory. We classify explicit types of sources in terms of their potential for synergy.We show that sources that emit uncorrelated signals provide no opportunity for synergetic coordination while sources that emit signals that are correlated in some way, do allow for strong synergy between searchers. These general considerations are crucial for designing optimal algorithms for particular search problems in real world settings.
KeywordsEntropy Decen Lost Peaked Sulton
Unable to display preview. Download preview PDF.
- 1.F. Bourgault, T. Furukawa, and H.F. Durrant-Whyte. Coordinated decentralized search for a lost target in a Bayesian world. Intelligent Robots and Systems, 2003. (IROS 2003). Proceedings. 2003 IEEE/RSJ International Conference on, 1:48, Oct. 2003.Google Scholar
- 3.R. S. Sulton and A. G. Barto. Reinforcement learning: an introduction. MIT Press, Cambrigde MA, 1998.Google Scholar
- 5.E. Bonabeau and G. Theraulaz. Swarm smarts. Scientific American, pages 72–79, Mar. 2000.Google Scholar
- 6.H. S. Seung, M. Opper, and H. Sompolinsky. Query by committee. In COLT '92: Proceedings of the fifth annual workshop on Computational learning theory, page 287, 1992.Google Scholar
- 7.Y. Freund, E. Shamir, and N. Tishby. Selective sampling using the query by committee algorithm. In Machine Learning, page 133, 1997.Google Scholar
- 12.E. Schneidman, W. Bialek, and M. J. Berry II. Synergy, redundancy, and independence in population codes. J. Neurosci., 23:11539, 2003.Google Scholar