Upcoming Seminars
December 2021
December 1, 2021 - 2:30pm | |||
---|---|---|---|
The Polyak-Lojasiewicz condition as a framework for over-parameterized optimization and its application to deep learningDecember 1, 2021 - 2:30pm Abstract: The success of deep learning is due, to a large extent, to the remarkable effectiveness of gradient-based optimization methods applied... |
Speaker: Mikhail Belkin, UCSD | ||
December 8, 2021 - 2:30pm | |||
A Fast, Stable QR Algorithm for the Diagonalization of Colleague MatricesDecember 8, 2021 - 2:30pm Abstract: The roots of a function represented by its Chebyshev expansion are known to be the eigenvalues of the so-called colleague matrix, which... |
Speaker: Vladimir Rokhlin, Yale | ||
December 15, 2021 - 2:30pm | |||
New Methods for Low-Rank Matrix DenoisingDecember 15, 2021 - 2:30pm Abstract: In this talk, I will describe a new class of methods for estimating a low-rank matrix from a noisy observed matrix, where the error is... |
Speaker: William Leeb, University of Minnesota |