The non-convex geometry of low-rank matrix optimization
نویسندگان
چکیده
منابع مشابه
The Non-convex Geometry of Low-rank Matrix Optimization
This work considers the minimization of a general convex function f(X) over the cone of positive semidefinite matrices whose optimal solution X⋆ is of low-rank. Standard first-order convex solvers require performing an eigenvalue decomposition in each iteration, severely limiting their scalability. A natural nonconvex reformulation of the problem factors the variable X into the product of a rec...
متن کاملThe Global Optimization Geometry of Low-Rank Matrix Optimization
In this paper we characterize the optimization geometry of a matrix factorization problem where we aim to find n×r and m×r matrices U and V such that UV T approximates a given matrixX. 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) = r, but also f...
متن کاملSketchy Decisions: Convex Low-Rank Matrix Optimization with Optimal Storage
This paper concerns a fundamental class of convex matrix optimization problems. It presents the first algorithm that uses optimal storage and provably computes a lowrank approximation of a solution. In particular, when all solutions have low rank, the algorithm converges to a solution. This algorithm, SketchyCGM, modifies a standard convex optimization scheme, the conditional gradient method, t...
متن کاملLow-rank optimization with convex constraints
The problem of low-rank approximation with convex constraints, which often appears in data analysis, image compression and model order reduction, is considered. Given a data matrix, the objective is to find an approximation of desired lower rank that fulfills the convex constraints and minimizes the distance to the data matrix in the Frobenius-norm. The problem of matrix completion can be seen ...
متن کاملLow Rank Matrix Approximation for Geometry Filtering
Wepropose a robust, anisotropic normal estimationmethod for both point clouds and meshes using a low rank matrix approximation algorithm. First, we compute a local feature descriptor for each point and find similar, non-local neighbors that we organize into a matrix. We then show that a low rank matrix approximation algorithm can robustly estimate normals for both point clouds and meshes. Furth...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Information and Inference: A Journal of the IMA
سال: 2018
ISSN: 2049-8772
DOI: 10.1093/imaiai/iay003