INTRODUCTION LECTURES
Introduction and presentation of the conferences by Frederic Barbaresco. VIDEO
Presentation of Geometric Sciences of Information and GSI 2021 by Frederic Barbaresco. VIDEO
LECTURES (90 min)
1. Langevin Dynamics
2. Computational Information Geometry:
2.1. Information Manifold modeled with Orlicz Spaces : Giovanni Pistone . VIDEO
2.2. Recent contributions to Distances and Information Geometry: a computational viewpoint : Frank Nielsen . VIDEO - SLIDES
3. Non-Equilibrium Thermodynamic Geometry
4. Geometric Mechanics
4.1. Galilean Mechanics and Thermodynamics of continua : Géry de Saxcé. VIDEO - SLIDES
4.2. Souriau-Casimir Lie Groups Thermodynamics and Machine Learning : Frederic Barbaresco. VIDEO - SLIDES
5. "Structure des Systèmes Dynamiques" (SSD) Jean-Marie Souriau’s book 50th Birthday Wikipedia page
5.1. Souriau Familly and "structure of motion": Jean-Marie Souriau, Michel Souriau, Paul Souriau and Etienne Souriau : Frederic Barbaresco . VIDEO - SLIDES
5.2. SSD Jean-Marie Souriau’s book 50th birthday: Géry de Saxcé SLIDES
KEYNOTES (60 min)
Learning Physics from Data : Francisco Chinesta . VIDEO VIDEO - SLIDES
Information Geometry and Integrable Systems : Jean-Pierre Françoise. VIDEO VIDEO - SLIDES
Learning with Few Labeled Data : Pratik Chaudhari . VIDEO - SLIDES
Information Geometry and Quantum Fields : Kevin Grosvenor SLIDES
Port Thermodynamic Systems Control : Bernhard Maschke . VIDEO - SLIDES
Dirac Structures in Nonequilibrium Thermodynamics : Hiroaki Yoshimura . VIDEO - SLIDES
Thermodynamic efficiency implies predictive inference : Susanne Still . VIDEO - SLIDES
Computational dynamics of reduced coupled multibody-fluid system in Lie group setting : Zdravko Terze . VIDEO - SLIDES
Exponential Family by Representation Theory : Koichi Tojo . VIDEO - SLIDES
Deep Learning as Optimal Control Problems and Structure Preserving Deep Learning : Elena Celledoni . VIDEO - SLIDES
Contact geometry and thermodynamical systems : Manuel de León. VIDEO - SLIDES
Mechanics of the probability simplex : Luigi Malagò. VIDEO - SLIDES
Covariant Momentum Map Thermodynamics : Goffredo Chirco. VIDEO - SLIDES
Sampling and statistical physics via symmetry : Steve Huntsman. VIDEO - SLIDES
Geometry of Measure-preserving Flows and Hamiltonian Monte Carlo : Alessandro Barp. VIDEO - SLIDES
Schroedinger's problem, Hamilton-Jacobi-Bellman equations and regularized Mass Transportation : Jean-Claude Zambrini. VIDEO - SLIDES
POSTERS
PDF of posters:
Registration fees for Summer Week is 450 euros, including catering (bedroom and 3 meals a dayon 5 days) and all accommodation on site: https://www.houches-school-physics.com/practical-information/facilities/ https://www.houches-school-physics.com/practical-information/your-stay/
Registration will be paid at Les Houches reception desk at your arrival by credit card (or VAD payment of your lab).
Any registration canceled less than two weeks before the arrival date will be due.
Arrival/Departure:
The arrival is Sunday July 26th starting from 3:00 pm. On the day of arrival, only the evening meal is planned. On Sunday, the secretariat is open from 6:00 pm to 7:30 pm. Summer Week will be closed Friday July 31st at 4 pm.
Access to Les Houches:
https://www.houches-school-physics.com/practical-information/access/
Ecole de Physique des Houches, 149 Chemin de la Côte, F-74310 Les Houches, France Les Houches is a village located in Chamonix valley, in the French Alps. Established in 1951, the Physics School is situated at 1150 m above sea level in natural surroundings, with breathtaking views on the Mont-Blanc mountain range.
https://houches-school-physics.com
Excursion:
Wednesday afternoon is free. Excursion could be organized to
· The Mer de Glace (Sea of Ice): It is the largest glacier in France, 7 km long and 200m deep and is one of the biggest attractions in the Chamonix Valley: https://www.chamonix.net/english/leisure/sightseeing/mer-de-glace
· L’Aiguille du midi: From its height of 3,777m, the Aiguille du Midi and its laid-out terraces offer a 360° view of all the French, Swiss and Italian Alps. A lift brings you to the summit terrace at 3,842m, where you will have a clear view of Mont Blanc: https://www.chamonix.com/aiguille-du-midi-step-into-the-void,80,en.html
]]>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
Non-Equilibrium Thermodynamic Geometry
A variational perspective of closed and open systems - François Gay-Balmaz
A Homogeneous Symplectic Approach - Arjan van der Schaft
Geometric Mechanics
Gallilean Mechanics & Thermodynamics of Continua - Géry de Saxcé
Souriau-Casimir Lie Groups Thermodynamics & Machine Learning – Frédéric Barbaresco
17 Keynotes (60 min)
Program Schedule
Mornings will be dedicated to 3 hours courses. Afternoons will be dedicated to long keynotes.
Poster session will be organized Wednesday morning.
]]>To submit a short paper or poster, please use the Easychair conference system:
https://easychair.org/conferences/?conf=spig20
Scientific rationale:
In the middle of the last century, Léon Brillouin in "The Science and The Theory of Information" or André Blanc-Lapierre in "Statistical Mechanics" forged the first links between the Theory of Information and Statistical Physics as precursors. In the context of Artificial Intelligence, machine learning algorithms use more and more methodological tools coming from the Physics or the Statistical Mechanics. The laws and principles that underpin this Physics can shed new light on the conceptual basis of Artificial Intelligence. Thus, the principles of Maximum Entropy, Minimum of Free Energy, Gibbs-Duhem's Thermodynamic Potentials and the generalization of François Massieu's notions of characteristic functions enrich the variational formalism of machine learning. Conversely, the pitfalls encountered by Artificial Intelligence to extend its application domains, question the foundations of Statistical Physics, such as the construction of stochastic gradient in large dimension, the generalization of the notions of Gibbs densities in spaces of more elaborate representation like data on homogeneous differential or symplectic manifolds, Lie groups, graphs, tensors, .... Sophisticated statistical models were introduced very early to deal with unsupervised learning tasks related to Ising-Potts models (the Ising-Potts model defines the interaction of spins arranged on a graph) of Statistical Physics. and more generally the Markov fields. The Ising models are associated with the theory of Mean Fields (study of systems with complex interactions through simplified models in which the action of the complete network on an actor is summarized by a single mean interaction in the sense of the mean field). The porosity between the two disciplines has been established since the birth of Artificial Intelligence with the use of Boltzmann machines and the problem of robust methods for calculating partition function. More recently, gradient algorithms for neural network learning use large-scale robust extensions of the natural gradient of Fisher-based Information Geometry (to ensure reparameterization invariance), and stochastic gradient based on the Langevin equation (to ensure regularization), or their coupling called "Natural Langevin Dynamics". Concomitantly, during the last fifty years, Statistical Physics has been the object of new geometrical formalizations (contact or symplectic geometry, ...) to try to give a new covariant formalization to the thermodynamics of dynamic systems. We can mention the extension of the symplectic models of Geometric Mechanics to Statistical Mechanics, or other developments such as Random Mechanics, Geometric Mechanics in its Stochastic version, Lie Groups Thermodynamic, and geometric modeling of phase transition phenomena. Finally, we refer to Computational Statistical Physics, which uses efficient numerical methods for large-scale sampling and multimodal probability measurements (sampling of Boltzmann-Gibbs measurements and calculations of free energy, metastable dynamics and rare events, ...) and the study of geometric integrators (Hamiltonian dynamics, symplectic integrators, ...) with good properties of covariances and stability (use of symmetries, preservation of invariants, ...). Machine learning inference processes are just beginning to adapt these new integration schemes and their remarkable stability properties to increasingly abstract data representation spaces. Artificial Intelligence currently uses only a very limited portion of the conceptual and methodological tools of Statistical Physics. The purpose of this conference is to encourage constructive dialogue around a common foundation, to allow the establishment of new principles and laws governing the two disciplines in a unified approach. But, it is also about exploring new « chemins de traverse ».
Organizers: