031w: Data Analytics, Networks and Approximation

Alexander Aptekarev, Keldysh Institute of Applied Mathematics
Panos Pardalos, Higher School of Economics, Nizhny Novgorod
Valery Kalyagin, Higher School of Economics, Nizhny Novgorod
Vladimir Lysov, Keldysh Institute of Applied Mathematics

Data analytics and in more general sense data analysis are in our days under extensive development in engineering and computer science with large areas of applications. However, it is recognized that there is a lack of mathematical foundations for many approaches and methods of data analytics. The proposed workshop is devoted to the development of mathematical aspects of data analytic methods related with network (graph based) models. Network models are ubiquitous in different fields of science and became more and more popular in data analysis and machine learning. Different aspects of network models in data analysis and machine learning will be discussed. In particular, it is planned to discuss the following problems: optimization of computational graph for deep learning, robustness of network models algorithms in machine learning and data analytics, network models under uncertainty, multi-level network models and others. Approximation aspect of network models which is crucial in computer simulations is covered as well.