Splitting numerical integration for matrix completion

02/14/2022
by   Qianqian Song, et al.
0

Low rank matrix approximation is a popular topic in machine learning. In this paper, we propose a new algorithm for this topic by minimizing the least-squares estimation over the Riemannian manifold of fixed-rank matrices. The algorithm is an adaptation of classical gradient descent within the framework of optimization on manifolds. In particular, we reformulate an unconstrained optimization problem on a low-rank manifold into a differential dynamic system. We develop a splitting numerical integration method by applying a splitting integration scheme to the dynamic system. We conduct the convergence analysis of our splitting numerical integration algorithm. It can be guaranteed that the error between the recovered matrix and true result is monotonically decreasing in the Frobenius norm. Moreover, our splitting numerical integration can be adapted into matrix completion scenarios. Experimental results show that our approach has good scalability for large-scale problems with satisfactory accuracy

READ FULL TEXT
research
08/18/2020

Robust Low-rank Matrix Completion via an Alternating Manifold Proximal Gradient Continuation Method

Robust low-rank matrix completion (RMC), or robust principal component a...
research
03/13/2022

On the analysis of optimization with fixed-rank matrices: a quotient geometric view

We study a type of Riemannian gradient descent (RGD) algorithm, designed...
research
04/24/2017

A Saddle Point Approach to Structured Low-rank Matrix Learning

We propose a novel optimization approach for learning a low-rank matrix ...
research
01/23/2020

A geometry based algorithm for dynamical low-rank approximation

In this paper, we propose a geometry based algorithm for dynamical low-r...
research
10/26/2018

Communication Efficient Parallel Algorithms for Optimization on Manifolds

The last decade has witnessed an explosion in the development of models,...
research
08/23/2013

Manopt, a Matlab toolbox for optimization on manifolds

Optimization on manifolds is a rapidly developing branch of nonlinear op...
research
11/17/2020

Recursive Importance Sketching for Rank Constrained Least Squares: Algorithms and High-order Convergence

In this paper, we propose a new ecursive mportance ketching algorithm fo...

Please sign up or login with your details

Forgot password? Click here to reset