Algorithmical and mathematical approaches of causal graph dynamics ; Approches informatique et mathématique des dynamiques causales de graphes

Cellular Automata constitute one of the most established model of discrete physical transformations that accounts for euclidean space. They implement three fundamental symmetries of physics: causality, homogeneity and finite density of information. Even though their origins lies in physics, they are widely used to model spatially distributed computation (self-replicating machines, synchronization problems,.), as well as a great variety of multi-agents phenomena (traffic jams, demographics,.). While being one of the most studied model of distributed computation, their rigidity forbids any trivial extension toward time-varying topology, which is a fundamental requirement when it comes to modelling phenomena in biology, sociology or physics: for instance when looking for a discrete formulation of general relativity. Causal graph dynamics generalize cellular automata to arbitrary, bounded degree, time-varying graphs. In this work, we generalize the fundamental structure results of cellular automata for this type of transformations. We endow our graphs with a compact metric space structure, and follow two approaches. An axiomatic approach based on the notions of continuity and shift-invariance, and a constructive approach, where a local rule is applied synchronously on every vertex of the graph. Compactness allows us to show the equivalence of these two definitions, extending the famous result of Curtis-Hedlund-Lyndon’s theorem. Another physics-inspired symmetry is then added to the model, namely reversibility. ; Le modèle des automates cellulaires constitue un des modèles le mieux établi de physique discrète sur espace euclidien. Ils implantent trois symétries fondamentales de la physique: la causalité, l'homogénéité et la densité finie de l'information. Bien que l'origine des automates cellulaires provienne de la physique, leur utilisation est très répandue comme modèles de calcul distribué dans l'espace (machines auto-réplicantes, problèmes de synchronisation,.), ou bien comme modèles de systèmes multi-agents ...