COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring. |
University of Cambridge > Talks.cam > Statistics > Histograms, Graph Limits, and the Asymptotic Behavior of Large Networks
Histograms, Graph Limits, and the Asymptotic Behavior of Large NetworksAdd to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact . Networks are fast becoming part of the modern statistical landscape. Yet we lack a full understanding of their large-sample properties in all but the simplest settings. This is hindering the development of models and estimation methods that admit theoretical performance guarantees. The asymptotic behavior of large networks can be exploited for nonparametric statistical inference, using recent developments from the theory of graph limits, and the corresponding analog of de Finetti’s theorem. A network histogram is obtained by fitting a stochastic blockmodel to a single observation of a network dataset. Blocks of edges play the role of histogram bins, and community sizes that of histogram bandwidths or bin sizes. Just as standard histograms allow for varying bandwidths, different blockmodel estimates can all be considered valid representations of an underlying probability model, subject to bandwidth constraints. We show that under these constraints, the mean integrated square error of the network histogram tends to zero as the network grows large, and we provide methods for optimal bandwidth selection-thus making the blockmodel a universal representation. With this insight, we discuss the interpretation of network communities in light of the fact that many different community assignments can all give an equally valid representation of the network. To demonstrate the fidelity-versus-interpretability tradeoff inherent in considering different numbers and sizes of communities, we show an example of detecting and describing new network community microstructure in political weblog data. This is joint work with Patrick Wolfe – UCL This talk is part of the Statistics series. This talk is included in these lists:
Note that ex-directory lists are not shown. |
Other listsNumber Theory Seminar Cambridge Canadian Club Events Cafe Scientifique SCAMPS 09 - One day Symposium Security-related talks Engineers Without BordersOther talksCyclic Peptides: Building Blocks for Supramolecular Designs Bears, Bulls and Boers: Market Making and Southern African Mining Finance, 1894-1899 Autumn Cactus & Succulent Show Phylogenetic hypothesis of the Oleeae tribe (Oleaceae) Diversification and molecular evolution patterns in plastid and nuclear ribosomal DNA 70th Anniversary Celebration 'The Japanese Mingei Movement and the art of Katazome' "Mechanosensitive regulation of cancer epigenetics and pluripotency" The Rise of Augmented Intelligence in Edge Networks 'Ways of Reading, Looking, and Imagining: Contemporary Fiction and Its Optics' Understanding Ellipsis: Corpus, Annotation, Theory |