"Learning with Structured Tensor Decompositions" by Prof. Anand Sarwate скачать в хорошем качестве

"Learning with Structured Tensor Decompositions" by Prof. Anand Sarwate

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. Note: This talk does not assume the audience has prior familiarity with tensor algebra.