Non-square matrix sensing without spurious local minima via the Burer-Monteiro approach

نویسندگان

  • Dohyung Park
  • Anastasios Kyrillidis
  • Constantine Caramanis
  • Sujay Sanghavi
چکیده

We consider the non-square matrix sensing problem, under restricted isometry property (RIP) assumptions. We focus on the non-convex formulation, where any rank-r matrix X ∈ R is represented as UV , where U ∈ R and V ∈ R. In this paper, we complement recent findings on the nonconvex geometry of the analogous PSD setting [5], and show that matrix factorization does not introduce any spurious local minima, under RIP.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

The non-convex Burer-Monteiro approach works on smooth semidefinite programs

Semidefinite programs (SDP’s) can be solved in polynomial time by interior point methods, but scalability can be an issue. To address this shortcoming, over a decade ago, Burer and Monteiro proposed to solve SDP’s with few equality constraints via rank-restricted, non-convex surrogates. Remarkably, for some applications, local optimization methods seem to converge to global optima of these nonc...

متن کامل

Local Minima and Convergence in Low-Rank Semidefinite Programming

The low-rank semidefinite programming problem LRSDPr is a restriction of the semidefinite programming problem SDP in which a bound r is imposed on the rank of X, and it is well known that LRSDPr is equivalent to SDP if r is not too small. In this paper, we classify the local minima of LRSDPr and prove the optimal convergence of a slight variant of the successful, yet experimental, algorithm of ...

متن کامل

No Spurious Local Minima in Nonconvex Low Rank Problems: A Unified Geometric Analysis

In this paper we develop a new framework that captures the common landscape underlying the common non-convex low-rank matrix problems including matrix sensing, matrix completion and robust PCA. In particular, we show for all above problems (including asymmetric cases): 1) all local minima are also globally optimal; 2) no highorder saddle points exists. These results explain why simple algorithm...

متن کامل

Convergence Analysis for Rectangular Matrix Completion Using Burer-Monteiro Factorization and Gradient Descent

We address the rectangular matrix completion problem by lifting the unknown matrix to a positive semidefinite matrix in higher dimension, and optimizing a nonconvex objective over the semidefinite factor using a simple gradient descent scheme. WithO(μr2κ2nmax(μ, log n)) random observations of a n1×n2 μ-incoherent matrix of rank r and condition number κ, where n = max(n1, n2), the algorithm line...

متن کامل

Global Convergence of Stochastic Gradient Descent for Some Non-convex Matrix Problems

The Burer-Monteiro [1] decomposition (X = Y Y T ) with stochastic gradient descent is commonly employed to speed up and scale up matrix problems including matrix completion, subspace tracking, and SDP relaxation. Although it is widely used in practice, there exist no known global convergence results for this method. In this paper, we prove that, under broad sampling conditions, a first-order ra...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2017