Tensor-Train Decomposition and Its Applications in Machine Learning

Explore the applications of tensor-train decomposition in machine learning through this 29-minute conference talk by Ivan Oseledets from the Skolkovo Institute of Science and Technology. Delivered as part of the "Tensor Methods and Emerging Applications to the Physical and Data Sciences 2021" workshop at the Institute for Pure & Applied Mathematics (IPAM), UCLA, this presentation provides an overview of how tensor-train decomposition and other tensor network models are utilized in various machine learning applications. Gain insights into the compression of neural networks, approximation of high-dimensional distributions, and analysis of the expressive power of deep neural networks. Enhance your understanding of advanced tensor methods and their practical implications in the field of machine learning and data science.