Nacionalni portal odprte znanosti

We will discuss how statistical physics techniques developed for the study of stochastic optimization problems can be used to design efficient algorithms for analyzing, controlling and activating extreme trajectories in a variety of cascade processes over graphs and lattices, in which nodes “activ ...

In this talk we firstly provide a rigorous probabilistic proof of the clustering phenomenon taking place in the space of solution of random combinatorial problems. Secondly we will discuss a generalization of the survey propagation equations efficiently exploring the clustered geometry. Finally, we ...

Deep networks are some of the most widely used tools in data science. Learning is in principle a hard problem in these systems, but in practice heuristic algorithms often find solutions with good generalization properties. We propose an explanation of this good performance in terms of a novel large ...