## Abstract

This book bridges the gap between advances in the communities of computer science and physics--namely machine learning and statistical physics. It contains diverse but relevant topics in statistical physics, complex systems, network theory, and machine learning. Examples of such topics are: predicting missing links, higher-order generative modeling of networks, inferring network structure by tracking the evolution and dynamics of digital traces, recommender systems, and diffusion processes.

The book contains extended versions of high-quality submissions received at the workshop, Dynamics On and Of Complex Networks (doocn.org), together with new invited contributions. The chapters will benefit a diverse community of researchers. The book is suitable for graduate students, postdoctoral researchers and professors of various disciplines including sociology, physics, mathematics, and computer science.

The book contains extended versions of high-quality submissions received at the workshop, Dynamics On and Of Complex Networks (doocn.org), together with new invited contributions. The chapters will benefit a diverse community of researchers. The book is suitable for graduate students, postdoctoral researchers and professors of various disciplines including sociology, physics, mathematics, and computer science.

Original language | English |
---|---|

Number of pages | 244 |

DOIs | |

Publication status | Published - 2019 |

Externally published | Yes |

Event | Dynamics on and of Complex Networks III, Machine Learning and Statistical Physics Approaches: DOOCN 2017 - Indianapolis, United States Duration: 19 Jun 2017 → 19 Jun 2017 |

### Publication series

Name | Springer Proceedings in Complexity |
---|