Block Bregman Majorization Minimization with Extrapolation
نویسندگان
چکیده
Related DatabasesWeb of Science You must be logged in with an active subscription to view this.Article DataHistorySubmitted: 9 July 2021Accepted: 21 September 2021Published online: 13 January 2022Keywordsinertial block coordinate method, majorization minimization, Bregman surrogate function, acceleration by extrapolation, orthogonal nonnegative matrix factorizationAMS Subject Headings90C26, 49M37, 65K05, 15A23, 15A83Publication DataISSN (online): 2577-0187Publisher: Society for Industrial and Applied MathematicsCODEN: sjmdaq
منابع مشابه
Generalized Majorization-Minimization
Non-convex optimization is ubiquitous in machine learning. The MajorizationMinimization (MM) procedure systematically optimizes non-convex functions through an iterative construction and optimization of upper bounds on the objective function. The bound at each iteration is required to touch the objective function at the optimizer of the previous bound. We show that this touching constraint is u...
متن کاملJoint minimization with alternating Bregman proximity operators
A systematic study of the proximity properties of Bregman distances is carried out. This investigation leads to the introduction of a new type of proximity operator which complements the usual Bregman proximity operator. We establish key properties of these operators and utilize them to devise a new alternating procedure for solving a broad class of joint minimization problems. We provide a com...
متن کاملMajorization-Minimization for Manifold Embedding
Nonlinear dimensionality reduction by manifold embedding has become a popular and powerful approach both for visualization and as preprocessing for predictive tasks, but more efficient optimization algorithms are still crucially needed. MajorizationMinimization (MM) is a promising approach that monotonically decreases the cost function, but it remains unknown how to tightly majorize the manifol...
متن کاملUndersampled Phase Retrieval via Majorization-Minimization
In the undersampled phase retrieval problem, the goal is to recover an N -dimensional complex signal x from only M < N noisy intensity measurements without phase information. This problem has drawn a lot of attention to reduce the number of required measurements since a recent theory established that M ≈ 4N intensity measurements are necessary and sufficient to recover a generic signal x. In th...
متن کاملDistributed Majorization-Minimization for Laplacian Regularized Problems
We consider the problem of minimizing a block separable convex function (possibly nondifferentiable, and including constraints) plus Laplacian regularization, a problem that arises in applications including model fitting, regularizing stratified models, and multi-period portfolio optimization. We develop a distributed majorizationminimization method for this general problem, and derive a comple...
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: SIAM journal on mathematics of data science
سال: 2022
ISSN: ['2577-0187']
DOI: https://doi.org/10.1137/21m1432661