A Block Inertial Bregman Proximal Algorithm for Nonsmooth Nonconvex Problems with Application to Symmetric Nonnegative Matrix Tri-Factorization
نویسندگان
چکیده
We propose BIBPA, a block inertial Bregman proximal algorithm for minimizing the sum of relatively smooth function (that is, concerning each block) and separable nonsmooth nonconvex functions. show that cluster points sequence generated by BIBPA are critical objective under standard assumptions, this converges globally when regularization satisfies Kurdyka-?ojasiewicz (KL) property. also provide convergence rate ?ojasiewicz inequality. apply to symmetric nonnegative matrix tri-factorization (SymTriNMF) problem, where we kernel functions SymTriNMF closed-form solutions subproblems BIBPA.
منابع مشابه
A Stochastic Nonconvex Splitting Method for Symmetric Nonnegative Matrix Factorization
where (a) because that E and Tr are both linear operators and Tr[E[ZZ ]] is certain positive number which is independent on the optimization variables, then this term can be replaced by another positive constant Tr[EZ[Z ]EZ[Z]]. Based on the equivalence between (13) and (14), we can apply the result shown in [28, Lemma 2]. Since the constraint set is polyhedral in the formulation (3), the linea...
متن کاملInertial proximal alternating minimization for nonconvex and nonsmooth problems
In this paper, we study the minimization problem of the type [Formula: see text], where f and g are both nonconvex nonsmooth functions, and R is a smooth function we can choose. We present a proximal alternating minimization algorithm with inertial effect. We obtain the convergence by constructing a key function H that guarantees a sufficient decrease property of the iterates. In fact, we prove...
متن کاملBenson's algorithm for nonconvex multiobjective problems via nonsmooth Wolfe duality
In this paper, we propose an algorithm to obtain an approximation set of the (weakly) nondominated points of nonsmooth multiobjective optimization problems with equality and inequality constraints. We use an extension of the Wolfe duality to construct the separating hyperplane in Benson's outer algorithm for multiobjective programming problems with subdifferentiable functions. We also fo...
متن کاملA Convergent Algorithm for Bi-orthogonal Nonnegative Matrix Tri-Factorization
Abstract. We extend our previous work on a convergent algorithm for uni-orthogonal nonnegative matrix factorization (UNMF) to the case where the data matrix is decomposed into three factors with two of them are constrained orthogonally and the third one is used to absorb the approximation error. Due to the way the factorization is performed, we name it as bi-orthogonal nonnegative matrix tri-fa...
متن کاملAn Inertial Tseng's Type Proximal Algorithm for Nonsmooth and Nonconvex Optimization Problems
We investigate the convergence of a forward-backward-forward proximal-type algorithm with inertial and memory effects when minimizing the sum of a nonsmooth function with a smooth one in the absence of convexity. The convergence is obtained provided an appropriate regularization of the objective satisfies the KurdykaLojasiewicz inequality, which is for instance fulfilled for semi-algebraic func...
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: Journal of Optimization Theory and Applications
سال: 2021
ISSN: ['0022-3239', '1573-2878']
DOI: https://doi.org/10.1007/s10957-021-01880-5