Friday, March 22, 2019 - 11:00am to Saturday, March 23, 2019 - 11:55am
Event Calendar Category
IDSS
Speaker Name
Eliran Subag
Affiliation
New York University
Building and Room number
E18-304
Abstract
The talk will focus on optimization on the high-dimensional sphere when the objective function is a linear combination of homogeneous polynomials with standard Gaussian coefficients. Such random processes are called spherical spin glasses in physics, and have been extensively studied since the 80s. I will describe certain geometric properties of spherical spin glasses unique to the full-RSB case, and explain how they can be used to design a polynomial time algorithm that finds points within small multiplicative error from the global minimum.
Biography
Eliran Subag is a Junior Fellow in the Simons Society of Fellows, at the Courant Institute, NYU.
MIT Statistics and Data Science Center host guest lecturers from around the world in this weekly seminar.