No Arabic abstract
Let $phi$ be a nontrivial function of $L^1(RR)$. For each $sgeq 0$ we put begin{eqnarray*} p(s)=-log int_{|t|geq s}|phi (t)|dt. end{eqnarray*} If $phi$ satisfies begin{equation} lim_{sto infty}frac{p(s)}{s}=infty ,label{170506.1} end{equation} we obtain asymptotic estimates of the size of small-valued sets $B_{epsilon}={xinRR : |hat{phi}(x)|leq epsilon, |x|leq R_{epsilon}}$ of Fourier transform begin{eqnarray*} hat{phi}(x)=int_{-infty}^{infty}e^{-ixt}phi (t)dt, xin RR, end{eqnarray*} in terms of $p(s)$ or in terms of its Young dual function begin{eqnarray*} p^{*}(t)=sup_{sgeq 0}[st-p(s)], tgeq 0. end{eqnarray*} Applying these results, we give an explicit estimate for the error of Tikhonovs regularization for the solution $f$ of the integral convolution equation begin{eqnarray*} int_{-infty}^{infty}f(t-s)phi (s)ds =g(t), end{eqnarray*} where $f,g in L^2(RR)$ and $phi$ is a nontrivial function of $L^1(RR)$ satisfying condition (ref{170506.1}), and $g,phi$ are known non-exactly. Also, our results extend some results of cite{tld} and cite{tqd}.
Most of the literature on the solution of linear ill-posed operator equations, or their discretization, focuses only on the infinite-dimensional setting or only on the solution of the algebraic linear system of equations obtained by discretization. This paper discusses the influence of the discretization error on the computed solution. We consider the situation when the discretization used yields an algebraic linear system of equations with a large matrix. An approximate solution of this system is computed by first determining a reduced system of fairly small size by carrying out a few steps of the Arnoldi process. Tikhonov regularization is applied to the reduced problem and the regularization parameter is determined by the discrepancy principle. Errors incurred in each step of the solution process are discussed. Computed examples illustrate the error bounds derived.
The logarithmic nonlinearity has been used in many partial differential equations (PDEs) for modeling problems in various applications.Due to the singularity of the logarithmic function, it introducestremendous difficulties in establishing mathematical theories, as well asin designing and analyzing numerical methods for PDEs with such nonlinearity. Here we take the logarithmic Schrodinger equation (LogSE)as a prototype model. Instead of regularizing $f(rho)=ln rho$ in theLogSE directly and globally as being done in the literature, we propose a local energy regularization (LER) for the LogSE byfirst regularizing $F(rho)=rholn rho -rho$ locally near $rho=0^+$ with a polynomial approximation in the energy functional of the LogSE and then obtaining an energy regularized logarithmic Schrodinger equation (ERLogSE) via energy variation. Linear convergence is established between the solutions of ERLogSE and LogSE in terms of a small regularization parameter $0<epll1$. Moreover, the conserved energy of the ERLogSE converges to that of LogSE quadratically, which significantly improvesthe linear convergence rate of the regularization method in the literature. Error estimates are alsopresented for solving the ERLogSE by using Lie-Trotter splittingintegrators. Numerical results are reported to confirm our errorestimates of the LER and of the time-splitting integrators for theERLogSE. Finally our results suggest that the LER performs better than regularizing the logarithmic nonlinearity in the LogSE directly.
We develop proper correction formulas at the starting $k-1$ steps to restore the desired $k^{rm th}$-order convergence rate of the $k$-step BDF convolution quadrature for discretizing evolution equations involving a fractional-order derivative in time. The desired $k^{rm th}$-order convergence rate can be achieved even if the source term is not compatible with the initial data, which is allowed to be nonsmooth. We provide complete error estimates for the subdiffusion case $alphain (0,1)$, and sketch the proof for the diffusion-wave case $alphain(1,2)$. Extensive numerical examples are provided to illustrate the effectiveness of the proposed scheme.
The discretization of certain integral equations, e.g., the first-kind Fredholm equation of Laplaces equation, leads to symmetric positive-definite linear systems, where the coefficient matrix is dense and often ill-conditioned. We introduce a new preconditioner based on a novel overlapping domain decomposition that can be combined efficiently with fast direct solvers. Empirically, we observe that the condition number of the preconditioned system is $O(1)$, independent of the problem size. Our domain decomposition is designed so that we can construct approximate factorizations of the subproblems efficiently. In particular, we apply the recursive skeletonization algorithm to subproblems associated with every subdomain. We present numerical results on problem sizes up to $16,384^2$ in 2D and $256^3$ in 3D, which were solved in less than 16 hours and three hours, respectively, on an Intel Xeon Platinum 8280M.
We consider the Serre system of equations which is a nonlinear dispersive system that models two-way propagation of long waves of not necessarily small amplitude on the surface of an ideal fluid in a channel. We discretize in space the periodic initial-value problem for the system using the standard Galerkin finite element method with smooth splines on a uniform mesh and prove an optimal-order $L^{2}$-error estimate for the resulting semidiscrete approximation. Using the fourth-order accurate, explicit, `classical Runge-Kutta scheme for time stepping we construct a highly accurate fully discrete scheme in order to approximate solutions of the system, in particular solitary-wave solutions, and study numerically phenomena such as the resolution of general initial profiles into sequences of solitary waves, and overtaking collisions of pairs of solitary waves propagating in the same direction with different speeds.