Lab Home | Phone | Search
	Center for Nonlinear Studies
	Home  ▶ People   Current   Executive Committee   Postdocs   Visitors   Students   Research   Publications  ▶ Conferences   Workshops   Sponsorship  ▶ Talks   Seminars   Postdoc Seminars Archive   Quantum Lunch   Quantum Lunch Archive   P/T Colloquia   Archive   Ulam Scholar     Postdoc Nominations  ▶ Student Requests   Student Program  ▶ Visitor Requests   Description   Past Visitors  ▶ Services   General     History of CNLS     Maps, Directions   CNLS Office   T-Division   LANL				Thursday, May 23, 20191:00 PM - 2:00 PMCNLS Conference Room (TA-3, Bldg 1690) Seminar Tensor decompositions and machine learning Ivan OseledetsSkolkovo Institute of Science and Technology In this talk I will discuss several SVD-based tensor decompositions (like tensor train), related algorithm and outline several recent works that connect tensor decomposition and machine learning. In short, tensor decompositions (and in general, factorization methods) can be very efficient in machine learning for different tasks, for the compression of neural networks, for the neural architectures, and also for the design of new machine learning models. Host: Ben Nebgen