Description du projet
Former des experts en optimisation pour donner un sens aux «big» data
L’objectif de la science des données est de tirer des conclusions en extrayant des informations significatives à partir d’une énorme quantité d’observations recueillies. Le domaine de la science des données comprend l’analyse de données, l’analyse prédictive, l’exploration de données et l’apprentissage automatique. L’optimisation apparaît comme la pierre angulaire de la plupart des méthodes théoriques et algorithmiques employées dans ce domaine. Le projet TraDE-OPT, financé par l’UE, s’attaquera aux défis que pose l’analyse de données «volumineuses», hétérogènes, incertaines ou partiellement observées. Plus précisément, le projet formera 15 experts à l’optimisation en matière de science des données. Le programme de formation offrira un solide bagage technique combiné à des compétences en termes d’employabilité: gestion, collecte de fonds, communication et planification de carrière.
Objectif
The main goal of TraDE-Opt is the education of 15 experts in optimization for data science, with a solid multidisciplinary background, able to advance the state-of-the-art. This field is fast-developing and its reach on our life is growing both in pervasiveness and impact. The central task in data science is to extract meaningful information from huge amounts of collected observations. Optimization appears as the cornerstone of most of the theoretical and algorithmic methods employed in this area. Indeed, recent results in optimization, but also in related areas such as functional analysis, machine learning, statistics, linear algebra, signal processing, systems and control theory, graph theory, data mining, etc. already provide powerful tools for exploring the mathematical properties of the proposed models and devising effective algorithms. Despite these advances, the nature of the data to be analyzed, that are “big”, heterogeneous, uncertain, or partially observed, still poses challenges and opportunities to modern optimization. The key aspect of the TraDE-Opt research is the exploitation of structure, in the data, in the model, or in the computational platform, to derive new and more efficient algorithms with guarantees on their computational performance, based on decomposition and incremental/stochastic strategies, allowing parallel and distributed implementations. Advances in these directions will determine impressive scalability benefits to the class of the considered optimization methods, that will allow the solution of real world problems. To achieve this goal, we will offer an innovative training program, giving a solid technical background combined with employability skills: management, fund raising, communication, and career planning skills. Integrated training of the fellows takes place at the host institute and by secondments, workshops, and schools. As a result, TraDE-Opt fellows will be prepared for outstanding careers in academia or industry.
Champ scientifique
- natural sciencesmathematicspure mathematicsalgebralinear algebra
- natural sciencescomputer and information sciencesdata sciencedata mining
- natural sciencesmathematicspure mathematicsmathematical analysisfunctional analysis
- natural sciencesmathematicspure mathematicsdiscrete mathematicsgraph theory
- natural sciencescomputer and information sciencesartificial intelligencemachine learning
Mots‑clés
Programme(s)
Régime de financement
MSCA-ITN - Marie Skłodowska-Curie Innovative Training Networks (ITN)Coordinateur
16126 Genova
Italie