Guaranteed Matrix Completion via Non-Convex Factorization
نویسندگان
چکیده
منابع مشابه
Matrix Completion via Non-convex Programming
We consider the matrix completion problem in the noisy setting. To achieve statistically efficient estimation of the unknown low-rank matrix, solving convex optimization problems with nuclear norm constraints has been both theoretically and empirically proved a successful strategy under certain regularity conditions. However, the bias induced by the nuclear norm penalty may compromise the estim...
متن کاملConvex Collective Matrix Factorization
In many applications, multiple interlinked sources of data are available and they cannot be represented by a single adjacency matrix, to which large scale factorization method could be applied. Collective matrix factorization is a simple yet powerful approach to jointly factorize multiple matrices, each of which represents a relation between two entity types. Existing algorithms to estimate par...
متن کاملBoolean Matrix Factorization and Noisy Completion via Message Passing
Boolean factor analysis is the task of decomposing a binary matrix to the Boolean product of two binary factors. This unsupervised data-analysis approach is desirable due to its interpretability, but hard to perform due its NP-hardness. A closely related problem is low-rank Boolean matrix completion from noisy observations. We treat these problems as maximum a posteriori inference problems, and...
متن کاملCSC 576: Matrix Factorization / Completion
where we use the Matlab language, for example, U(:, 1 : r) denotes the first r columns of U . Note that the optimal solution is not unique. One can get another one by scaling H∗ and W ∗, for example, αH∗,W ∗/α for any α 6= 0. However, if the matrix A is too large, the SVD computation is too expensive, since the complexity of SVD is in the order of O(mnmin(m,n)). In the following, we will introd...
متن کاملNon-negative Matrix Factorization via Archetypal Analysis
Given a collection of data points, non-negative matrix factorization (NMF) suggests to express them as convex combinations of a small set of ‘archetypes’ with non-negative entries. This decomposition is unique only if the true archetypes are non-negative and sufficiently sparse (or the weights are sufficiently sparse), a regime that is captured by the separability condition and its generalizati...
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: IEEE Transactions on Information Theory
سال: 2016
ISSN: 0018-9448,1557-9654
DOI: 10.1109/tit.2016.2598574