GSI’21 - Geometric Science of Information
LEARNING GEOMETRIC STRUCTURES
Co-organized by SEE, SCAI Sorbonne and ELLIS Paris Unit
As for GSI’13/GSI’15/GSI’17/GSI’19, the objective of this 5th SEE GSI’21 conference, hosted in Sorbonne University, is to bring together pure/applied mathematicians and engineers, with common interest for Geometric tools and their applications for Information analysis and Learning. It emphasizes an active participation of young researchers to discuss emerging areas of collaborative research on “Geometric Science of Information and their Applications”.
Current and ongoing uses of Information Geometry Manifolds in applied mathematics are the following: Advanced Signal/Image/Video Processing, Complex Data Modeling and Analysis, Information Ranking and Retrieval, Coding, Cognitive Systems, Optimal Control, Statistics on Manifolds, Topology/Machine/Deep Learning, Physics and Learning, Geometry of Quantum states, Speech/sound recognition, natural language treatment, Small/Big Data Analytics, Learning for Robotics, etc., which are substantially relevant for industry.
The Conference will be therefore held in areas of topics of mutual interest with the aim to:
• Provide an overview on the most recent state-of-the-art
• Exchange mathematical information/knowledge/expertise in the area
This conference will be an interdisciplinary event and will unify skills from Geometry, Probability and Information Theory.
Proceedings are published in Springer's Lecture Note in Computer Science series. SPRINGER & MDPI will sponsor best paper & best poster Awards.
Gala Diner will take place in Paris Downtown.
• Paper submission opening : 2nd of January 2021
• Deadline for 8 pages SPRINGER LNCS format: 14th of February 2021
• Notification of acceptance: 25th of April 2021
• Final paper submission: 9th of May 2021
Paper templates and Guideline on GSI’21 website at “Author Instructions”.
Advanced information on article submission and publication
As for previous editions, GSI’21 Proceedings will be published in SPRINGER LNCS
8 pages SPRINGER LNCS format is required for Initial paper submission.
Athor Guideline is available on the website
• Max Welling (Informatics Institute, University of Amsterdam and Qualcomm Technologies) : Exploring Quantum Statistics for Machine Learning
• Michel Broniatowski (LPSM lab, Sorbonne Université, Paris) : Some insights on statistical divergences and choice of models
• Maurice de Gosson (Faculty of Mathematics, NuHAG group, University of Vienna) : Gaussian states from a symplectic geometry point of view
• Jean Petitot (Centre d'Analyse et de Mathématiques, Sociales, École des Hautes Études, Paris) : The primary visual cortex as a Cartan engine
Provisional topics of interests
• Geometric Deep Learning (ELLIS session)
• Probability on Riemannian Manifolds
• Optimization on Manifold
• Shape Space & Statistics on non-linear data
• Lie Group Machine Learning
• Harmonic Analysis on Lie Groups
• Statistical Manifold & Hessian Information Geometry
• Deformed entropy, cross-entropy, and relative entropy
• Non-parametric Information Geometry
• Computational Information Geometry
• Distance and Divergence Geometries
• Divergence Statistics
• Optimal Transport & Learning
• Transport information geometry
• Around Schrödinger's problem
• Information Geometry in Physics
• Geometry of Hamiltonian Monte Carlo
• Statistics, Information & Topology
• Graph Hyperbolic Embedding & Learning
• Inverse problems: Bayesian and Machine Learning interaction
• Integrable Systems & Information Geometry
• Geometric structures in thermodynamics and statistical physics
• Contact Geometry & Hamiltonian Control
• Geometric and structure preserving discretizations
• Geometric & Symplectic Methods for Quantum Systems
• Geometry of Quantum States
• Geodesic Methods with Constraints
• Probability Density Estimation & Sampling in High Dimension
• Geometry of Tensor-Valued Data
• Geometric Mechanics
• Contact Hamiltonian systems
• Stochastic Geometric Mechanics
• Geometric Robotics & Learning
• Topological and geometrical structures in neurosciences
• Geometric Structures Coding & Learning Libraries (geomstats, pyRiemann , Pot…)
(c) GdR 720 ISIS - CNRS - 2011-2020.