SVM-Optimization and Steepest-Descent Line Search
نویسندگان
چکیده
We consider (a subclass of) convex quadratic optimization problems and analyze decomposition algorithms that perform, at least approximately, steepest-descent exact line search. We show that these algorithms, when implemented properly, are within ǫ of optimality after O(log 1/ǫ) iterations for strictly convex cost functions, and after O(1/ǫ) iterations in the general case. Our analysis is general enough to cover the algorithms that are used in software packages like SVMTorch and (first or second order) LibSVM. To the best of our knowledge, this is the first paper coming up with a convergence rate for these algorithms without introducing unnecessarily restrictive assumptions.
منابع مشابه
A Free Line Search Steepest Descent Method for Solving Unconstrained Optimization Problems
In this paper, we solve unconstrained optimization problem using a free line search steepest descent method. First, we propose a double parameter scaled quasi Newton formula for calculating an approximation of the Hessian matrix. The approximation obtained from this formula is a positive definite matrix that is satisfied in the standard secant relation. We also show that the largest eigen value...
متن کاملSteepest Descent Preconditioning for Nonlinear GMRES Optimization
Steepest descent preconditioning is considered for the recently proposed nonlinear generalized minimal residual (N-GMRES) optimization algorithm for unconstrained nonlinear optimization. Two steepest descent preconditioning variants are proposed. The first employs a line search, while the second employs a predefined small step. A simple global convergence proof is provided for the NGMRES optimi...
متن کاملConstrained Nonlinear Optimal Control via a Hybrid BA-SD
The non-convex behavior presented by nonlinear systems limits the application of classical optimization techniques to solve optimal control problems for these kinds of systems. This paper proposes a hybrid algorithm, namely BA-SD, by combining Bee algorithm (BA) with steepest descent (SD) method for numerically solving nonlinear optimal control (NOC) problems. The proposed algorithm includes th...
متن کاملHandling Nonpositive Curvature in a Limited Memory Steepest Descent Method
We propose a limited memory steepest descent method for solving unconstrained optimization problems. As a steepest descent method, the step computation in each iteration only requires the evaluation of a gradient of the objective function and the calculation of a scalar stepsize. When employed to solve certain convex problems, our method reduces to a variant of the limited memory steepest desce...
متن کاملAugmented Downhill Simplex a Modified Heuristic Optimization Method
Augmented Downhill Simplex Method (ADSM) is introduced here, that is a heuristic combination of Downhill Simplex Method (DSM) with Random Search algorithm. In fact, DSM is an interpretable nonlinear local optimization method. However, it is a local exploitation algorithm; so, it can be trapped in a local minimum. In contrast, random search is a global exploration, but less efficient. Here, rand...
متن کامل