Nonsmooth rank-one matrix factorization landscape
نویسندگان
چکیده
We provide the first positive result on nonsmooth optimization landscape of robust principal component analysis, to best our knowledge. It is object several conjectures and remains mostly uncharted territory. identify a necessary sufficient condition for absence spurious local minima in rank-one case. Our proof exploits subdifferential regularity objective function order eliminate existence quantifier from first-order optimality known as Fermat’s rule.
منابع مشابه
Weighted Rank-One Binary Matrix Factorization
Mining discrete patterns in binary data is important for many data analysis tasks, such as data sampling, compression, and clustering. An example is that replacing individual records with their patterns would greatly reduce data size and simplify subsequent data analysis tasks. As a straightforward approach, rank-one binary matrix approximation has been actively studied recently for mining disc...
متن کاملNonconvex Matrix Factorization from Rank-One Measurements
We consider the problem of recovering low-rank matrices from random rank-one measurements, which spans numerous applications including covariance sketching, phase retrieval, quantum state tomography, and learning shallow polynomial neural networks, among others. Our approach is to directly estimate the low-rank factor by minimizing a nonconvex quadratic loss function via vanilla gradient descen...
متن کاملFast Nonnegative Matrix Factorization with Rank-one ADMM
Nonnegative matrix factorization (NMF), which aims to approximate a data matrix with two nonnegative low rank matrix factors, is a popular dimensionality reduction and clustering technique. Due to the non-convex formulation and the nonnegativity constraints over the two low rank matrix factors (with rank r > 0), it is often difficult to solve NMF efficiently and accurately. Recently, the altern...
متن کاملA Non-convex One-Pass Framework for Generalized Factorization Machines and Rank-One Matrix Sensing
We develop an efficient alternating framework for learning a generalized version of Factorization Machine (gFM) on steaming data with provable guarantees. When the instances are sampled from d dimensional random Gaussian vectors and the target second order coefficient matrix in gFM is of rank k, our algorithm converges linearly, achieves O(ǫ) recovery error after retrieving O(kd log(1/ǫ)) train...
متن کاملA Non-convex One-Pass Framework for Generalized Factorization Machine and Rank-One Matrix Sensing
We develop an efficient alternating framework for learning a generalized version of Factorization Machine (gFM) on steaming data with provable guarantees. When the instances are sampled from d dimensional random Gaussian vectors and the target second order coefficient matrix in gFM is of rank k, our algorithm converges linearly, achieves O( ) recovery error after retrieving O(kd log(1/ )) train...
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: Optimization Letters
سال: 2021
ISSN: ['1862-4480', '1862-4472']
DOI: https://doi.org/10.1007/s11590-021-01819-9