Joint Structures and Common Foundation of Statistical Physics, Information Geometry and Inference for Learning 26 th July to 31 st July 2020 Registration, Poster Submission: https://franknielsen.github.io/SPIG-LesHouches2020/ 8 Lectures (90 min) Langevin Dynamics: Old and News (x 2) – Eric Moulines Computational Information Geometry Divergence based Machine Learning – Frank Nielsen Non-Parametric and Orlicz Spaces – Giovanni Pistone Non-Equilibrium Thermodynamic Geometry Evolution Equations for Open Systems - François Gay-Balmaz An Homogeneous Symplectic Approach - Arjan van der Schaft Geometric Mechanics Gallilean Mechanics & Thermodynamics of Continua - Géry de Saxcé Souriau-Casimir Lie Groups Thermodynamics & Machine Learning – F. Barbaresco 15 Keynotes (60 min) SGD & Variational Inference - Pratik Chaudhari Fast MCMC via Lie Group - Steve Huntsman HMC on Symmetric/Homogeneous Spaces - Alessandro Barp Exponential Familly by Representation Theory - Koichi Tojo Learning Physics from Data - Francisco Chinesta Information Geometry & Integrable Hamiltonian - Jean-Pierre Françoise Information Geometry & Quantum Field - Ro Jefferson Physical Limits to Information Processing - Susanne Still Diffeological Fisher Metric - Hông Vân Lê Deep Learning as Optimal Control - Elena Celledoni Dirac structures in Thermodynamics - Hiroaki Yoshimura Port Thermodynamic Systems Control - Bernhard Maschke Covariant Momentum Map Thermodynamics - Goffredo Chirco Contact Hamiltonian Systems - Manuel de León Multibody-Fluid System Dynamics in Lie group - Zdravko Terze SPIGL’20

Joint Structures and Common Foundation of Statistical ......Geometric Mechanics Gallilean Mechanics & Thermodynamics of Continua - Géry de Saxcé Souriau-Casimir Lie Groups Thermodynamics

Download PDF Report

Upload
others
View
11
Download
0

Embed Size (px)

Citation preview

Page 1: Joint Structures and Common Foundation of Statistical ......Geometric Mechanics Gallilean Mechanics & Thermodynamics of Continua - Géry de Saxcé Souriau-Casimir Lie Groups Thermodynamics

Joint Structures and Common Foundation of Statistical Physics, Information Geometry and Inference for Learning

26th July to 31st July 2020Registration, Poster Submission: https://franknielsen.github.io/SPIG-LesHouches2020/

8 Lectures (90 min)Langevin Dynamics: Old and News (x 2) – Eric Moulines Computational Information GeometryDivergence based Machine Learning – Frank NielsenNon-Parametric and Orlicz Spaces – Giovanni PistoneNon-Equilibrium Thermodynamic GeometryEvolution Equations for Open Systems - François Gay-BalmazAn Homogeneous Symplectic Approach - Arjan van der SchaftGeometric MechanicsGallilean Mechanics & Thermodynamics of Continua - Géry de SaxcéSouriau-Casimir Lie Groups Thermodynamics & Machine Learning – F. Barbaresco

15 Keynotes (60 min)SGD & Variational Inference - Pratik ChaudhariFast MCMC via Lie Group - Steve HuntsmanHMC on Symmetric/Homogeneous Spaces - Alessandro BarpExponential Familly by Representation Theory - Koichi TojoLearning Physics from Data - Francisco ChinestaInformation Geometry & Integrable Hamiltonian - Jean-Pierre FrançoiseInformation Geometry & Quantum Field - Ro JeffersonPhysical Limits to Information Processing - Susanne StillDiffeological Fisher Metric - Hông Vân LêDeep Learning as Optimal Control - Elena CelledoniDirac structures in Thermodynamics - Hiroaki YoshimuraPort Thermodynamic Systems Control - Bernhard MaschkeCovariant Momentum Map Thermodynamics - Goffredo ChircoContact Hamiltonian Systems - Manuel de LeónMultibody-Fluid System Dynamics in Lie group - Zdravko Terze

SPIGL’20

https://franknielsen.github.io/SPIG-LesHouches2020/