MADMM: A Generic Algorithm for Non-smooth Optimization on Manifolds
نویسندگان
چکیده
Numerous problems in machine learning are formulated as optimization with manifold constraints. In this paper, we propose the Manifold alternating directions method of multipliers (MADMM), an extension of the classical ADMM scheme for manifold-constrained non-smooth optimization problems and show its application to several challenging problems in dimensionality reduction, data analysis, and manifold learning.
منابع مشابه
Mangasarian-Fromovitz and Zangwill Conditions For Non-Smooth Infinite Optimization problems in Banach Spaces
In this paper we study optimization problems with infinite many inequality constraints on a Banach space where the objective function and the binding constraints are Lipschitz near the optimal solution. Necessary optimality conditions and constraint qualifications in terms of Michel-Penot subdifferential are given.
متن کاملA NOVEL META-HEURISTIC ALGORITHM: TUG OF WAR OPTIMIZATION
This paper presents a novel population-based meta-heuristic algorithm inspired by the game of tug of war. Utilizing a sport metaphor the algorithm, denoted as Tug of War Optimization (TWO), considers each candidate solution as a team participating in a series of rope pulling competitions. The teams exert pulling forces on each other...
متن کاملMultiobjective Imperialist Competitive Evolutionary Algorithm for Solving Nonlinear Constrained Programming Problems
Nonlinear constrained programing problem (NCPP) has been arisen in diverse range of sciences such as portfolio, economic management etc.. In this paper, a multiobjective imperialist competitive evolutionary algorithm for solving NCPP is proposed. Firstly, we transform the NCPP into a biobjective optimization problem. Secondly, in order to improve the diversity of evolution country swarm, and he...
متن کاملOptimal Trajectory Planning of a Box Transporter Mobile Robot
This paper aims to discuss the requirements of safe and smooth trajectory planning of transporter mobile robots to perform non-prehensile object manipulation task. In non-prehensile approach, the robot and the object must keep their grasp-less contact during manipulation task. To this end, dynamic grasp concept is employed for a box manipulation task and corresponding conditions are obtained an...
متن کاملDirac operators on manifolds with periodic ends
This paper studies Dirac operators on end-periodic spin manifolds of dimension at least 4. We provide a necessary and sufficient condition for such an operator to be Fredholm for a generic end-periodic metric. We make use of end-periodic Dirac operators to give an analytical interpretation of an invariant of non-orientable smooth 4-manifolds due to Cappell and Shaneson. From this interpretation...
متن کامل