arXiv subjects

Heping Wang

Publications and source records attributed to Heping Wang.

33 records · Page 2Linked to original sources

arXiv2021

Approximation and quadrature by weighted least squares polynomials on the sphere

Given a sequence of Marcinkiewicz-Zygmund inequalities in $L_2$ on a usual compact space $\mathcal M$, Gröchenig introduced the weighted least squares polynomials and the least squares quadrature from pointwise samples of a function, and obtained approximation theorems and quadrature errors. In this paper we obtain approximation theorems and quadrature errors on the sphere which are optimal. We also give upper bounds of the operator norms of the weighted least squares operators.

math.NA↗

arXiv2021

On the power of standard information for tractability for $L_2$-approximation in the randomized setting

We study approximation of multivariate functions from a separable Hilbert space in the randomized setting with the error measured in the weighted $L_2$ norm. We consider algorithms that use standard information $Λ^{\rm std}$ consisting of function values or general linear information $Λ^{\rm all}$ consisting of arbitrary linear functionals. We use the weighted least squares regression algorithm to obtain the upper estimates of the minimal randomized error using $Λ^{\rm std}$. We investigate the equivalences of various notions of algebraic and exponential tractability for $Λ^{\rm std}$ and $Λ^{\rm all}$ for the normalized or absolute error criterion. We show that in the randomized setting for the normalized or absolute error criterion, the power of $Λ^{\rm std}$ is the same as that of $Λ^{\rm all}$ for all notions of exponential and algebraic tractability without any condition. Specifically, we solve four Open Problems 98, 100-102 as posed by E.Novak and H.Woźniakowski in the book: Tractability of Multivariate Problems, Volume III: Standard Information for Operators, EMS Tracts in Mathematics, Zürich, 2012.

math.NA↗

arXiv2020

Outlier-robust Kalman filters with mixture correntropy

We consider the robust filtering problem for a nonlinear state-space model with outliers in measurements. To improve the robustness of the traditional Kalman filtering algorithm, we propose in this work two robust filters based on mixture correntropy, especially the double-Gaussian mixture correntropy and Laplace-Gaussian mixture correntropy. We have formulated the robust filtering problem by adopting the mixture correntropy induced cost to replace the quadratic one in the conventional Kalman filter for measurement fitting errors. In addition, a tradeoff weight coefficient is introduced to make sure the proposed approaches can provide reasonable state estimates in scenarios where measurement fitting errors are small. The formulated robust filtering problems are iteratively solved by utilizing the cubature Kalman filtering framework with a reweighted measurement covariance. Numerical results show that the proposed methods can achieve a performance improvement over existing robust solutions.

stat.ME↗

arXiv2019

Average case tractability of additive random fields with Korobov kernels

We investigate average case tractability of approximation of additive random fields with marginal random processes corresponding to the Korobov kernels for the non-homogeneous case. We use the absolute error criterion (ABS) or the normalized error criterion (NOR). We show that the problem is always polynomially tractable for ABS or NOR, and give sufficient and necessary conditions for strong polynomial tractability for ABS or NOR.

math.NA↗

arXiv2019

Strong equivalences of approximation numbers and tractability of weighted anisotropic Sobolev embeddings

In this paper, we study multivariate approximation defined over weighted anisotropic Sobolev spaces which depend on two sequences ${\bf a}=\{a_j\}_{j\geq1}$ and ${\bf b}=\{b_j\}_{j\geq1}$ of positive numbers. We obtain strong equivalences of the approximation numbers, and necessary and sufficient conditions on ${\bf a}$, ${\bf b}$ to achieve various notions of tractability of the weighted anisotropic Sobolev embeddings.

math.NA↗

arXiv2019

Tractability of non-homogeneous tensor product problems in the worst case setting

We study multivariate linear tensor product problems with some special properties in the worst case setting. We consider algorithms that use finitely many continuous linear functionals. We use a unified method to investigate tractability of the above multivariate problems, and obtain necessary and sufficient conditions for strong polynomial tractability, polynomial tractability, quasi-polynomial tractability, uniformly weak tractability, $(s,t)$-weak tractability, and weak tractability. Our results can apply to multivariate approximation problems with kernels corresponding to Euler kernels, Wiener kernels, Korobov kernels, Gaussian kernels, and analytic Korobov kernels.

math.NA↗

arXiv2018

Maximum Correntropy Derivative-Free Robust Kalman Filter and Smoother

We consider the problem of robust estimation involving filtering and smoothing for nonlinear state space models which are disturbed by heavy-tailed impulsive noises. To deal with heavy-tailed noises and improve the robustness of the traditional nonlinear Gaussian Kalman filter and smoother, we propose in this work a general framework of robust filtering and smoothing, which adopts a new maximum correntropy criterion to replace the minimum mean square error for state estimation. To facilitate understanding, we present our robust framework in conjunction with the cubature Kalman filter and smoother. A half-quadratic optimization method is utilized to solve the formulated robust estimation problems, which leads to a new maximum correntropy derivative-free robust Kalman filter and smoother. Simulation results show that the proposed methods achieve a substantial performance improvement over the conventional and existing robust ones with slight computational time increase.

stat.AP↗

arXiv2018

A note about EC-$(s,t)$-weak tractability of multivariate approximation with analytic Korobov kernels

This note is devoted to discussing multivariate approximation of continuous functions on $[0,1]^d$ with analytic Korobov kernels in the worst and average case settings. We only consider algorithms that use finitely many evaluations of arbitrary continuous linear functionals. We study EC-$(s, t)$-weak tractability under the absolute or normalized error criterion, and obtain necessary and sufficient conditions for $0<\min(s,t)<1$ and $\max(s,t)\le 1$ in the worst case setting and for $s,t>0$ in the average case setting.

math.NA↗

arXiv2018

Average Case $(s, t)$-weak tractability of non-homogenous tensor product problems

We study $d$-variate problem in the average case setting with respect to a zero-mean Gaussian measure. The covariance kernel of this Gaussian measure is a product of univariate kernels and satisfies some special properties. We study $(s, t)$-weak tractability of this multivariate problem, and obtain a necessary and sufficient condition for $s>0$ and $t\in(0,1)$. Our result can apply to the problems with covariance kernels corresponding to Euler and Wiener integrated processes, Korobov kernels, and analytic Korobov kernels.

math.NA↗

arXiv2018

Average Case tractability of multivariate approximation with Gaussian kernels

We study the problem of approximating functions of $d$ variables in the average case setting for the $L_2$ space $L_{2,d}$ with the standard Gaussian weight equipped with a zero-mean Gaussian measure. The covariance kernel of this Gaussian measure takes the form of a Gaussian kernel with non-increasing positive shape parameters $γ_j^2$ for $j = 1, 2, \dots, d$. The error of approximation is defined in the norm of $L_{2,d}$. We study the average case error of algorithms that use at most $n$ arbitrary continuous linear functionals. The information complexity $n(\varepsilon, d)$ is defined as the minimal number of linear functionals which are needed to find an algorithm whose average case error is at most $\varepsilon$. We study different notions of tractability or exponentially-convergent tractability (EC-tractability) which the information complexity $n(\varepsilon, d)$ describe how behaves as a function of $d$ and $\varepsilon^{-1}$ or as one of $d$ and $(1+\ln\varepsilon^{-1})$. We find necessary and sufficient conditions on various notions of tractability and EC-tractability in terms of shape parameters. In particular, for any positive $s>0$ and $t\in(0,1)$ we obtain that the sufficient and necessary condition on $γ^2_ j$ for which $$\lim_{d+\varepsilon^{-1}\to\infty}\frac{n(\varepsilon,d)}{\varepsilon^{-s}+d^t}=0$$ holds is $$ \lim_{j\to \infty}j^{1-t}γ_j^2\,\ln^+ γ_j^{-2}=0,$$where $\ln^+ x=\max(1,\ln x)$.

math.NA↗

arXiv2017

Approximation numbers of Sobolev and Gevrey type embeddings on the sphere and on the ball -- Preasymptotics, asymptotics, and tractability

In this paper, we investigate optimal linear approximations ($n$-approximation numbers ) of the embeddings from the Sobolev spaces $H^r\ (r>0)$ for various equivalent norms and the Gevrey type spaces $G^{α,β}\ (α,β>0)$ on the sphere $\Bbb S^d$ and on the ball $\Bbb B^d$, where the approximation error is measured in the $L_2$-norm. We obtain preasymptotics, asymptotics, and strong equivalences of the above approximation numbers as a function in $n$ and the dimension $d$. We emphasis that all equivalence constants in the above preasymptotics and asymptotics are independent of the dimension $d$ and $n$. As a consequence we obtain that for the absolute error criterion the approximation problems $I_d: H^{r}\to L_2$ are weakly tractable if and only if $r>1$, not uniformly weakly tractable, and do not suffer from the curse of dimensionality. We also prove that for any $α,β>0$, the approximation problems $I_d: G^{α,β}\to L_2$ are uniformly weakly tractable, not polynomially tractable, and quasi-polynomially tractable if and only if $α\ge 1$.

math.CA↗

arXiv2016

Preasymptotics and asymptotics of approximation numbers of anisotropic Sobolev embeddings

In this paper, we obtain the preasymptotic and asymptotic behavior and strong equivalences of the approximation numbers of the embeddings from the anisotropic Sobolev spaces $W_2^{\bf R}(\Bbb T^d)$ to $L_2(\Bbb T^d)$. We also get the preasymptotic behavior of the approximation numbers of the embeddings from the limit spaces $W_2^{\infty}(\Bbb T^d)$ of the anisotropic Sobolev spaces $W_2^{\bf R}(\Bbb T^d)$ to $L_2(\Bbb T^d)$. We show that both the above embedding problems are intractable and do not suffer from the curse of dimensionality.

math.NA↗

arXiv2016

Probabilistic and average linear widths of weighted Sobolev spaces on the ball equipped with a Gaussian measure

Let $L_{q,μ}$, $1\leq q\leq\infty$, denotes the weighted $L_q$ space of functions on the unit ball $\Bbb B^d$ with respect to weight $(1-\|x\|_2^2)^{μ-\frac12},\,μ\ge 0$, and let $W_{2,μ}^r$ be the weighted Sobolev space on $\Bbb B^d$ with a Gaussian measure $ν$. We investigate the probabilistic linear $(n,δ)$-widths $λ_{n,δ}(W_{2,μ}^r,ν,L_{q,μ})$ and the $p$-average linear $n$-widths $λ_n^{(a)}(W_{2,μ}^r,μ,L_{q,μ})_p$, and obtain their asymptotic orders for all $1\le q\le \infty$ and $0<p<\infty$.

math.CA↗

arXiv2015

On filtered polynomial approximation on the sphere

This paper considers filtered polynomial approximations on the unit sphere $\mathbb{S}^d\subset \mathbb{R}^{d+1}$, obtained by truncating smoothly the Fourier series of an integrable function $f$ with the help of a "filter" $h$, which is a real-valued continuous function on $[0,\infty)$ such that $h(t)=1$ for $t\in[0,1]$ and $h(t)=0$ for $t\ge2$. The resulting "filtered polynomial approximation" (a spherical polynomial of degree $2L-1$) is then made fully discrete by approximating the inner product integrals by an $N$-point cubature rule of suitably high polynomial degree of precision, giving an approximation called "filtered hyperinterpolation". In this paper we require that the filter $h$ and all its derivatives up to $\lfloor\tfrac{d-1}{2}\rfloor$ are absolutely continuous, while its right and left derivatives of order $\lfloor \tfrac{d+1}{2}\rfloor$ exist everywhere and are of bounded variation. Under this assumption we show that for a function $f$ in the Sobolev space $W^s_p(\mathbb{S}^d),\ 1\le p\le \infty$, both approximations are of the optimal order $ L^{-s}$, in the first case for $s>0$ and in the second fully discrete case for $s>d/p$.

math.CA↗

arXiv2007

Positive Cubature formulas and Marcinkiewicz-Zygmund inequalities on spherical caps

Let $Π_n^d$ denote the space of all spherical polynomials of degree at most $n$ on the unit sphere $\sph$ of $\mathbb{R}^{d+1}$, and let $d(x, y)$ denote the usual geodesic distance $\arccos x\cdot y$ between $x, y\in \sph$. Given a spherical cap $$ B(e,\al)=\{x\in\sph: d(x, e) \leq \al\}, (e\in\sph, \text{$\al\in (0,π)$ is bounded away from $π$}),$$ we define the metric $$ρ(x,y):=\frac 1{\al} \sqrt{(d(x, y))^2+\al(\sqrt{\al-d(x, e)}-\sqrt{\al-d(y,e)})^2}, $$ where $x, y\in B(e,\al)$. It is shown that given any $\be\ge 1$, $1\leq p<\infty$ and any finite subset $\Ld$ of $B(e,\al)$ satisfying the condition $\dmin_{\sub{ξ,η\in \Ld ξ\neq η}} ρ(ξ,η) \ge \f \da n$ with $\da\in (0,1]$, there exists a positive constant $C$, independent of $\al$, $n$, $\Ld$ and $\da$, such that, for any $f\inΠ_{n}^d$, \begin{equation*} \sum_{\og\in \Ld} (\max_{x,y\in B_ρ(\og, \be\da/n)}|f(x)-f(y)|^p) |B_ρ(\og, \da/n)| \le (C \dz)^p \int_{B(e,\al)} |f(x)|^p d\sa(x),\end{equation*} where $d\sa(x)$ denotes the usual Lebesgue measure on $\sph$, $$B_ρ(x, r)=\Bl\{y\in B(e,\al): ρ(y,x)\leq r\Br\}, (r>0),$$ and $$\Bl|B_ρ(x, \f\da n)\Br|=\int_{B_ρ(x, \da/n)} d\sa(y) \sim \al ^{d}\Bl[ (\f{\da}n)^{d+1}+ (\f\da n)^{d} \sqrt{1-\f{d(x, e)}\al}\Br].$$ As a consequence, we establish positive cubature formulas and Marcinkiewicz-Zygmund inequalities on the spherical cap $B(e,\al)$.

math.CA↗