Convergence Analysis of Perturbed Feasible Descent Methods
نویسندگان
چکیده
منابع مشابه
Convergence Analysis of Perturbed Feasible Descent Methods
We develop a general approach to convergence analysis of feasible descent methods in the presence of perturbations. The important novel feature of our analysis is that perturbations need not tend to zero in the limit. In that case, standard convergence analysis techniques are not applicable. Therefore, a new approach is needed. We show that, in the presence of perturbations, a certain e-approxi...
متن کاملIteration Complexity of Feasible Descent Methods Iteration Complexity of Feasible Descent Methods for Convex Optimization
In many machine learning problems such as the dual form of SVM, the objective function to be minimized is convex but not strongly convex. This fact causes difficulties in obtaining the complexity of some commonly used optimization algorithms. In this paper, we proved the global linear convergence on a wide range of algorithms when they are applied to some non-strongly convex problems. In partic...
متن کاملConvergence Properties of Feasible Descent Methods for Solving Variational Inequalities in Banach Spaces
This work is concerned with the analysis of convergence properties of feasible descent methods for solving monotone variational inequalities in Banach spaces.
متن کاملLinear Convergence of Randomized Feasible Descent Methods Under the Weak Strong Convexity Assumption
In this paper we generalize the framework of the Feasible Descent Method (FDM) to a Randomized (R-FDM) and a Randomized Coordinate-wise Feasible Descent Method (RCFDM) framework. We show that many machine learning algorithms, including the famous SDCA algorithm for optimizing the SVM dual problem, or the stochastic coordinate descent method for the LASSO problem, fits into the framework of RC-F...
متن کاملConvergence Analysis of Sampling Methods for Perturbed Lipschitz Functions
In this short note we observe that results of Dennis and Audet extend naturally to a wide variety of deterministic sampling methods. For bound-constrained problems, we show that any method based on coordinate search which includes a sufficiently rich set of directions, for example random directions at each state of the sampling, will, when applied to Lipschitz continuous problems, have cluster ...
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: 1997
ISSN: 0022-3239,1573-2878
DOI: 10.1023/a:1022602123316