EXPANSIONS OF STEP-TRANSITION OPERATORS OF MULTI-STEP METHODS AND ORDER BARRIERS FOR DAHLQUIST PAIRS

Using least parameters, we expand the step-transition operator of any linear multi-step method （LMSM） up to O（τ^s＋5） with order s = 1 and rewrite the expansion of the steptransition operator for s = 2 （obtained by the second author in a former paper）. We prove that in the conjugate relation G3^λτ o G1^τ =G2^τ o G3^λτ with G1 being an LMSM,（1） theorder of G2 can not be higher than that of G1; （2） if G3 is also an LMSM and G2 is a symplectic B-series, then the orders of G1, G2 and G3 must be 2, 2 and 1 respectively.     

A modified spectral conjugate gradient projection algorithm for total variation image restoration

In this study, a modified spectral conjugate gradient projection method is presented to solve total variation image restoration, which is transferred into the nonlinear constrained optimization with the closed constrained set. The global convergence of the proposed scheme is analyzed. In the end, some numerical results illustrate the efficiency of this method.     

Cluster robustness of preconditioned gradient subspace iteration eigensolvers

The paper presents convergence estimates for a class of iterative methods for solving partial generalized symmetric eigenvalue problems whereby a sequence of subspaces containing approximations to eigenvectors is generated by combining the Rayleigh-Ritz and the preconditioned steepest descent/ascent methods. The paper uses a novel approach of studying the convergence of groups of eigenvalues, rather than individual ones, to obtain new convergence estimates for this class of methods that are cluster robust, i.e. do not involve distances between computed eigenvalues.     

Conjugacy for normal or abnormal linear Bolza problems

For certain Bolza problems with linear dynamics, two sets extending the notion of conjugate points in the calculus of variations are introduced. Independently of nonsingularity assumptions, their emptiness, in one case without normality assumptions, is shown to be equivalent to a second order necessary condition. A comparison with other notions available in the literature is given.     

Sharp Geometric Poincare Inequalities for Vector Fields and Non-Doubling Measures

We derive Sobolev–Poincaré inequalities that estimatethe L^q(d µ) norm of a function on a metric ball when µis an arbitrary Borel measure. The estimate is in terms of theL¹(d ) norm on the ball of a vector field gradient of the function,where d dx is a power of a fractional maximal function of µ.We show that the estimates are sharp in several senses, andwe derive isoperimetric inequalities as corollaries. 1991 MathematicsSubject Classification: 46E35, 42B25.     

Duality theorems on an infinite network *

We study conjugate duality for optimization problems on an infinite, but locally finite network with countable node set X and countable are set Y In contrast to earlier approaches we do not employ Hilbert or Banach space methods. Instead we work in the spaces R^X and R^Y which are siven their Droduct toDolosv, As an application we obtain generalizations of some basic inverse relations from discrete potential theory     

A composite step bi-conjugate gradient algorithm for nonsymmetric linear systems

The Bi-Conjugate Gradient (BCG) algorithm is the simplest and most natural generalization of the classical conjugate gradient method for solving nonsymmetric linear systems. It is well-known that the method suffers from two kinds of breakdowns. The first is due to the breakdown of the underlying Lanczos process and the second is due to the fact that some iterates are not well-defined by the Galerkin condition on the associated Krylov subspaces. In this paper, we derive a simple modification of the BCG algorithm, the Composite Step BCG (CSBCG) algorithm, which is able to compute all the well-defined BCG iterates stably, assuming that the underlying Lanczos process does not break down. The main idea is to skip over a step for which the BCG iterate is not defined.The work of this author was supported by the Office of Naval Research under contract N00014-89J-1440.The work of this author was supported by the Office of Naval Research under contracts N00014-90J-1695 and N00014-92J-1890, the Department of Energy under contract DE-FG03-87ER25307, the National Science Foundation under contracts ASC 90-03002 and 92-01266, and the Army Research Office under contract DAAL03-91-G-0150. Part of this work was completed during a visit to the Computer Science Dept., The Chinese University of Hong Kong.     

Cascadic multilevel methods for ill-posed problems

Multilevel methods are popular for the solution of well-posed problems, such as certain boundary value problems for partial differential equations and Fredholm integral equations of the second kind. However, little is known about the behavior of multilevel methods when applied to the solution of linear ill-posed problems, such as Fredholm integral equations of the first kind, with a right-hand side that is contaminated by error. This paper shows that cascadic multilevel methods with a conjugate gradient-type method as basic iterative scheme are regularization methods. The iterations are terminated by a stopping rule based on the discrepancy principle.     

On Some Generalized Polyhedral Convex Constructions

Generalized polyhedral convex sets, generalized polyhedral convex functions on locally convex Hausdorff topological vector spaces, and the related constructions such as sum of sets, sum of functions, directional derivative, infimal convolution, normal cone, conjugate function, subdifferential are studied thoroughly in this paper. Among other things, we show how a generalized polyhedral convex set can be characterized through the finiteness of the number of its faces. In addition, it is proved that the infimal convolution of a generalized polyhedral convex function and a polyhedral convex function is a polyhedral convex function. The obtained results can be applied to scalar optimization problems described by generalized polyhedral convex sets and generalized polyhedral convex functions.