Chairmen Welcome

Welcome to “Geometric Science of Information” 2017 Conference in Paris

On behalf of both the organizing and the scientific committees, it is our great pleasure to welcome all delegates, representatives and participants from around the world to the third International SEE conference on “Geometric Science of Information” (GSI’17), hosted in Paris, last quarter 2017.
GSI’17 benefits from scientific sponsor and financial sponsors.
The 3-day conference is also organized in the frame of the relations set up between SEE and scientific institutions or academic laboratories: Ecole Polytechnique, Ecole des Mines ParisTech, INRIA, Supélec, Université Paris-Sud, Institut Mathématique de Bordeaux, Sony Computer Science Laboratories, Institut Mines Télécom.
We would like to express all our thanks to the local organizers for hosting this second scientific´ event at the interface between Geometry, Probability and Information Geometry.
The GSI conference cycle has been initiated by the Brillouin Seminar Team. The GSI’17 event has been motivated in the continuity of first initiatives launched in 2013 ( and consolidated in 2015 ( We mention that in 2011, we organized an indo-french workshop on “Matrix Information Geometry” that yielded an edited book in 2013.
The technical program of GSI’17 covers all the main topics and highlights in the domain of “Geometric Science of Information” including Information Geometry Manifolds of structured data/information and their advanced applications. This proceedings consists solely of original research papers that have been carefully peer-reviewed by two or three experts before, and revised before acceptance.
The GSI17 program includes a renown invited speaker and three (3) keynote distinguished speakers.

Historical background

As for theGSI’13 and GSI’15, GSI’17 addresses inter-relations between different mathematical domains like shape spaces (geometric statistics on manifolds and Lie groups, deformations in shape space, ...), probability/optimization & algorithms on manifolds (structured matrix manifold, structured data/Information, ...), relational and discrete metric spaces (graph metrics, distance geometry, relational analysis,...), computational and Hessian information geometry, algebraic/infinite dimensional/Banach information manifolds, divergence geometry, tensor-valued morphology, optimal transport theory, manifold & topology learning, ... and applications like geometries of audio-processing, inverse problems and signal processing. GSI’15 topics were enriched with contributions from (Stochastic) Geometric Mechanics and Geometric Model of Quantum Physics. GSI’17 will integer new topics as Geometric Robotics, Information Structure on Neuroscience, Stochastic Calculus of variations (Malliavin Calculus), Geometric Deep Learning, …
At the turn of the century, new and fruitful interactions were discovered between several branches of science: Information Science (information theory, digital communications, statistical signal processing,), Mathematics (group theory, geometry and topology, probability, statistics, sheaves theory,...) and Physics (geometric mechanics, thermodynamics, statistical physics, quantum mechanics, ...). GSI conference cycle is a tentative to discover joint mathematical structures to all these disciplines by elaboration of a “General Theory of Information” embracing physics science, information science, and cognitive science in a global scheme.
Frank Nielsen, co-chair
Ecole Polytechnique, Palaiseau, France
Sony Computer Science Laboratories, Tokyo, Japan
Frédéric Barbaresco, co-chair
President of SEE ISIC Club (Ingéniérie des Systèmes d'Information et de Communications)
Representative of KTD PCC (Key Technology Domain / Processing, Computing & Cognition ) Board, THALES LAND & AIR SYSTEMS, France
Silvère Bonnabel, co-chair
Mines ParisTech
PSL Research University
Centre for Robotics, Paris, France.
Groupes / audience: