Program

Program
See attached Poster, Scientific Program and Poster Program.
8 Lectures (90 min)

Langevin Dynamics: Old and News (x 2) – Eric Moulines

Computational Information Geometry
On statistical distances and information geometry for ML – Frank Nielsen
Information Manifold modeled with Orlicz Spaces – Giovanni Pistone 
NonEquilibrium Thermodynamic Geometry
A variational perspective of closed and open systems  François GayBalmaz
A Homogeneous Symplectic Approach  Arjan van der Schaft 
Geometric Mechanics
Gallilean Mechanics & Thermodynamics of Continua  Géry de Saxcé
SouriauCasimir Lie Groups Thermodynamics & Machine Learning – Frédéric Barbaresco
17 Keynotes (60 min)
 Learning with Few Labeled Data  Pratik Chaudhari
 Sampling and statistical physics via symmetry  Steve Huntsman
 The Bracket Geometry of MeasurePreserving Flows and Diffusions  Alessandro Barp
 Exponential Family by Representation Theory  Koichi Tojo
 Learning Physics from Data  Francisco Chinesta
 Information Geometry and Integrable Hamiltonian  JeanPierre Françoise
 Information Geometry and Quantum Fields  Kevin Grosvenor
 Thermodynamic efficiency implies predictive inference Susanne Still
 Diffeological Fisher Metric  Hông Vân Lê
 Deep Learning as Optimal Control  Elena Celledoni
 Schroedinger's problem, HamiltonJacobiBellman equations and regularized Mass Transportation  JeanClaude Zambrini
 Mechanics of the probability simplex  Luigi Malagò
 Dirac structures in nonequilibrium thermodynamics  Hiroaki Yoshimura
 Port Thermodynamic Systems Control  Bernhard Maschke
 Covariant Momentum Map Thermodynamics  Goffredo Chirco
 Contact geometry and thermodynamical systems  Manuel de León
 Computational dynamics of multibodyfluid system in Lie group setting Zdravko Terze
Program Schedule
Mornings will be dedicated to 3 hours courses. Afternoons will be dedicated to long keynotes.
Poster session will be organized Wednesday morning.
