Sorry, you need to enable JavaScript to visit this website.

The Landscape of Non-convex Quadratic Feasibility

Primary tabs

Citation Author(s):
Lalit Jain, Laura Balzano
Submitted by:
Amanda Bower
Last updated:
19 April 2018 - 2:10pm
Document Type:
Presentation Slides
Document Year:
2018
Event:
Presenters Name:
Amanda Bower
Paper Code:
4494

Abstract 

Abstract: 

Motivated by applications such as ordinal embedding and collaborative ranking, we formulate homogeneous quadratic feasibility as an unconstrained, non-convex minimization problem. Our work aims to understand the landscape (local minimizers and global minimizers) of the non-convex objective, which corresponds to hinge losses arising from quadratic constraints. Under certain assumptions, we give necessary conditions for non-global, local minimizers of our objective and additionally show that in two dimensions, every local minimizer is a global minimizer. Empirically, we demonstrate that finding feasible points by solving the unconstrained optimization problem with stochastic gradient descent works reliably by utilizing large initializations.

up
0 users have voted:

Dataset Files

ICASSP_v4.pdf

(309)