Thu, 6-Feb-2020 / 4:30pm / Packard 101
I will discuss a new strategy to find stationary points of non-convex functions in low-dimensional spaces. In particular we resolve an open problem from 1993 by Stephen A. Vavasis on the complexity of this problem in 2D.
Joint work with Dan Mikulincer.
Sebastien Bubeck is a Principal Researcher in the Machine Learning and Optimization group at Microsoft Research. He joined MSR in 2014, after three years as an assistant professor at Princeton University (ORFE), one-year postdoc at Pompeu Fabra University with Gabor Lugosi, and graduate studies at INRIA in France with Remi Munos. He received several best paper awards at machine learning conferences (NeurIPS 2018 best paper, ALT 2018 best student paper in joint work with MSR interns, COLT 2016 best paper, and COLT 2009 best student paper), and was a 2015 Alfred P. Sloan Research Fellow in Computer Science.
Packard Building
Electrical Engineering Department
350 Jane Stanford Way
Stanford, CA 94305-9515
Thursdays, 4pm, Packard 202
