Block-proximal methods with spatially adapted acceleration
نویسندگان
چکیده
منابع مشابه
Block-proximal methods with spatially adapted acceleration
We study and develop (stochastic) primal–dual block-coordinate descent methods based on the method of Chambolle and Pock. Our methods have known convergence rates for the iterates and the ergodic gap: O(1/N 2) if each each block is strongly convex, O(1/N ) if no convexity is present, and more generally a mixed rate O(1/N 2) + O(1/N ) for strongly convex blocks, if only some blocks are strongly ...
متن کاملStochastic Proximal Gradient Descent with Acceleration Techniques
Proximal gradient descent (PGD) and stochastic proximal gradient descent (SPGD) are popular methods for solving regularized risk minimization problems in machine learning and statistics. In this paper, we propose and analyze an accelerated variant of these methods in the mini-batch setting. This method incorporates two acceleration techniques: one is Nesterov’s acceleration method, and the othe...
متن کاملWeights in block iterative methods
In this paper we introduce a sequential block iterative method and its simultaneous version with op-timal combination of weights (instead of convex combination) for solving convex feasibility problems.When the intersection of the given family of convex sets is nonempty, it is shown that any sequencegenerated by the given algorithms converges to a feasible point. Additionally for linear feasibil...
متن کاملAbstract Fixpoint Computations with Numerical Acceleration Methods
Fixpoint Computations with Numerical Acceleration Methods Olivier Bouissou and Yassamine Seladji CEA, LIST, Laboratory for the Modeling and Analysis of Interacting Systems 91191 Gif-sur-Yvette, France
متن کاملSolving Structured Sparsity Regularization with Proximal Methods
Proximal methods have recently been shown to provide effective optimization procedures to solve the variational problems defining the !1 regularization algorithms. The goal of the paper is twofold. First we discuss how proximal methods can be applied to solve a large class of machine learning algorithms which can be seen as extensions of !1 regularization, namely structured sparsity regularizat...
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: ETNA - Electronic Transactions on Numerical Analysis
سال: 2019
ISSN: 1068-9613,1068-9613
DOI: 10.1553/etna_vol51s15