The Effect of Parametrization on Nonconvex Optimization Landscapes - Seminar
Offered By: Instituto de Matemática Pura e Aplicada via YouTube
Course Description
Overview
Explore a 54-minute seminar by Joe Kileel on "The Effect of Parametrization on Nonconvex Optimization Landscapes" presented at the Instituto de Matemática Pura e Aplicada. Delve into the relationship between paired optimization problems through smooth parametrization of domains, examining how this affects optimization landscapes. Discover a new geometric framework for studying parametrizations and their impact on landscapes, with applications in low-rank matrix and tensor optimization, semidefinite programming, neural network training, and symmetry quotienting. Gain insights from this joint work with Eitan Levin and Nicolas Boumal, presented as part of the Seminário Centro PI series.
Syllabus
(11/11/2022) - Seminário Centro PI - Joe Kileel
Taught by
Instituto de Matemática Pura e Aplicada
Related Courses
Graph Partitioning and ExpandersStanford University via NovoEd Convex Optimization
Stanford University via edX Approximation Algorithms Part II
École normale supérieure via Coursera The State of JuMP - Progress and Future Plans
The Julia Programming Language via YouTube Quantum Algorithms for Optimization - Quantum Colloquium
Simons Institute via YouTube