Graph signals : learning and optimization perspectives

2-3 mai 2019
Université de Montpellier - Montpellier (France)
Handling large datasets has become a major challenge in fields such as applied mathematics, machine learning and statistics. However, many methods proposed in the literature do not take into account the fine structures (geometric or not) behind the underlying data. Such structures can often be modeled by graph theory Though many worldwide companies such as Google, Facebook or Twitter, have built their success on extracting information from signals natively lying on graphs, a refined analysis of the underlying graph influence is still missing. From a theoretical perspective this underlying structure is often neglected, or roughly incorporated in the model or in the analysis. The same limits appears in genomics (determining a map of interactions between genes and proteins), epidemiology, neuro-science or transportation networks. For this workshop, we plan to gather researchers at the frontiere between various fields to exchange state of the art methods and tools to address the new challenges raised by the large scale data-sets now commonly encountered by practitioners. More precisely, the research presented during this workshop will be at the interface between machine learning, statistics, applied mathematics, optimization, network physics, and life sciences.
Discipline scientifique : Mathématiques - Bio-Informatique, Biologie Systémique - Traitement du signal et de l'image - Apprentissage Machine - Machine Learning

Lieu de la conférence
Personnes connectées : 108 |  Contact |  À propos |  RSS