Problem of the Week
Hilton Memorial Lecture
Speaker: Ming Yuan (Columbia)
Title: Spectral Learning for High Dimensional Tensors
Abstract: Matrix perturbation bounds developed by Weyl, Davis, Kahan and Wedin and others play a central role in many statistical and machine learning problems. I shall discuss some of the recent progresses in developing similar bounds for higher order tensors. I will highlight the intriguing differences from matrices, and explore their implications in spectral learning problems.