On Tuesday, July 2nd, Prof. Anand Sarwate from Rutgers University give his Distinguished Lecture:
Title: "Learning with Structured Tensor Decompositions”
Abstract: Many measurements or signals are multidimensional, or tensor-valued. Vectorizing tensor data for statistical and machine learning tasks often results in having to fit a very large number of parameters. Using tensor decompositions to model such data can give a flexible and useful modeling framework whose complexity can adapt to the amount of data available. This talk will introduce classical decompositions (CP, Tucker) as well as more recent ones (tensor train, block tensor decomposition, and low separation rank) and show how they can be used to learn scalable representations for tensor-valued data and make predictions from tensor-valued data. Time permitting, we will describe applications in federated learning as well as open problems for future research.
The event will be transmitted via Teams: (https://teams.microsoft.com/l/meetup-join/19%3ameeting_MTgzMjdkYjUtZDYxNi00NmUxLTk0YjAtNDQwZTIxYWQzMDdh%40thread.v2/0?context=%7b%22Tid%22%3a%225f84c4ea-370d-4b9e-830c-756f8bf1b51f%22%2c%22Oid%22%3a%22b4bdccba-f532-48cd-8208-457d6bc3086c%22%7d)
Co-sponsored by: Universidad Rey Juan Carlos, Universidad Carlos III de Madrid
Speaker(s): Dr. Anand Sarwate,
Virtual: https://events.vtools.ieee.org/m/425691