Loading [a11y]/accessibility-menu.js
Linearized ADMM Converges to Second-Order Stationary Points for Non-Convex Problems | IEEE Journals & Magazine | IEEE Xplore

Linearized ADMM Converges to Second-Order Stationary Points for Non-Convex Problems


Abstract:

In this work, a gradient-based primal-dual method of multipliers is proposed for solving a class of linearly constrained non-convex problems. We show that with random ini...Show More

Abstract:

In this work, a gradient-based primal-dual method of multipliers is proposed for solving a class of linearly constrained non-convex problems. We show that with random initialization of the primal and dual variables, the algorithm is able to compute second-order stationary points (SOSPs) with probability one. Further, we present applications of the proposed method in popular signal processing and machine learning problems such as decentralized matrix factorization and decentralized training of overparameterized neural networks. One of the key steps in the analysis is to construct a new loss function for these problems such that the required convergence conditions (especially the gradient Lipschitz conditions) can be satisfied without changing the global optimal points.
Published in: IEEE Transactions on Signal Processing ( Volume: 69)
Page(s): 4859 - 4874
Date of Publication: 02 August 2021

ISSN Information:

Funding Agency:


References

References is not available for this document.