Solving Overparametrized Systems of Nonlinear Equations
Offered By: Institute for Pure & Applied Mathematics (IPAM) via YouTube
Course Description
Overview
Explore a 58-minute lecture on solving overparametrized systems of nonlinear equations presented by Andrea Montanari from Stanford University at IPAM's EnCORE Workshop. Delve into the problem of solving equations F(x)=0, where x represents d-dimensional unit vectors and D is a non-linear map with independent, rotationally invariant Gaussian processes. Examine the study under proportional asymptotics as n and d diverge, with their ratio converging to alpha 0. Discover upper and lower bounds, conjectures about solution existence, and the potential for polynomial-time algorithms. Investigate generalizations of this model and gain insights into the optimization landscape of overparametrized neural networks. Learn about the joint work with Eliran Subag and its implications for computational and statistical gaps in learning and optimization.
Syllabus
Andrea Montanari - Solving overparametrized systems of nonlinear equations - IPAM at UCLA
Taught by
Institute for Pure & Applied Mathematics (IPAM)
Related Courses
Statistical Shape Modelling: Computing the Human AnatomyUniversity of Basel via FutureLearn Stochastic processes
Higher School of Economics via Coursera Introduction to Scientific Machine Learning
Purdue University via edX Machine Learning 1 - 2020
YouTube Signals and Systems II
METUopencouseware via YouTube