The Global Optimization Geometry of Low-Rank Matrix Optimization

TL;DR

This paper analyzes the optimization landscape of low-rank matrix problems, showing that under certain conditions, local search algorithms can efficiently find global solutions due to the problem's geometric properties.

Contribution

It characterizes the global geometry of rank-constrained matrix optimization problems and proves the absence of spurious local minima under broad conditions.

Findings

Objective function satisfies the robust strict saddle property.

No spurious local minima in matrix factorization problems.

Gradient descent converges globally with random initialization.

Abstract

This paper considers general rank-constrained optimization problems that minimize a general objective function $f(X)$ over the set of rectangular $n\times m$ matrices that have rank at most $r$. To tackle the rank constraint and also to reduce the computational burden, we factorize $X$ into $UV^T$ where $U$ and $V$ are $n\times r$ and $m\times r$ matrices, respectively, and then optimize over the small matrices $U$ and $V$. We characterize the global optimization geometry of the nonconvex factored problem and show that the corresponding objective function satisfies the robust strict saddle property as long as the original objective function $f$ satisfies restricted strong convexity and smoothness properties, ensuring global convergence of many local search algorithms (such as noisy gradient descent) in polynomial time for solving the factored problem. We also provide a comprehensive analysis for the optimization geometry of a matrix factorization problem where we aim to find $n\times r$ and $m\times r$ matrices $U$ and $V$ such that $UV^T$ approximates a given matrix $X^\star$. Aside from the robust strict saddle property, we show that the objective function of the matrix factorization problem has no spurious local minima and obeys the strict saddle property not only for the exact-parameterization case where $rank(X^\star) = r$, but also for the over-parameterization case where $rank(X^\star) < r$ and the under-parameterization case where $rank(X^\star) > r$. These geometric properties imply that a number of iterative optimization algorithms (such as gradient descent) converge to a global solution with random initialization.