亚洲男人的天堂2018av,欧美草比,久久久久久免费视频精选,国色天香在线看免费,久久久久亚洲av成人片仓井空

Stochastic gradient descent with momentum (SGDM) is the dominant algorithm in many optimization scenarios, including convex optimization instances and non-convex neural network training. Yet, in the stochastic setting, momentum interferes with gradient noise, often leading to specific step size and momentum choices in order to guarantee convergence, set aside acceleration. Proximal point methods, on the other hand, have gained much attention due to their numerical stability and elasticity against imperfect tuning. Their stochastic accelerated variants though have received limited attention: how momentum interacts with the stability of (stochastic) proximal point methods remains largely unstudied. To address this, we focus on the convergence and stability of the stochastic proximal point algorithm with momentum (SPPAM), and show that SPPAM allows a faster linear convergence rate compared to stochastic proximal point algorithm (SPPA) with a better contraction factor, under proper hyperparameter tuning. In terms of stability, we show that SPPAM depends on problem constants more favorably than SGDM, allowing a wider range of step size and momentum that lead to convergence.

We derive a priori error of the Godunov method for the multidimensional Euler system of gas dynamics. To this end we apply the relative energy principle and estimate the distance between the numerical solution and the strong solution. This yields also the estimates of the $L^2$-norm of errors in density, momentum and entropy. Under the assumption that the numerical density and energy are bounded, we obtain a convergence rate of $1/2$ for the relative energy in the $L^1$-norm. Further, under the assumption -- the total variation of numerical solution is bounded, we obtain the first order convergence rate for the relative energy in the $L^1$-norm. Consequently, numerical solutions (density, momentum and entropy) converge in the $L^2$-norm with the convergence rate of $1/2$. The numerical results presented for Riemann problems are consistent with our theoretical analysis.

We observe $n$ pairs of independent random variables $X_{1}=(W_{1},Y_{1}),\ldots,X_{n}=(W_{n},Y_{n})$ and assume, although this might not be true, that for each $i\in\{1,\ldots,n\}$, the conditional distribution of $Y_{i}$ given $W_{i}$ belongs to a given exponential family with real parameter $\theta_{i}^{\star}=\boldsymbol{\theta}^{\star}(W_{i})$ the value of which is an unknown function $\boldsymbol{\theta}^{\star}$ of the covariate $W_{i}$. Given a model $\boldsymbol{\overline\Theta}$ for $\boldsymbol{\theta}^{\star}$, we propose an estimator $\boldsymbol{\widehat \theta}$ with values in $\boldsymbol{\overline\Theta}$ the construction of which is independent of the distribution of the $W_{i}$. We show that $\boldsymbol{\widehat \theta}$ possesses the properties of being robust to contamination, outliers and model misspecification. We establish non-asymptotic exponential inequalities for the upper deviations of a Hellinger-type distance between the true distribution of the data and the estimated one based on $\boldsymbol{\widehat \theta}$. We deduce a uniform risk bound for $\boldsymbol{\widehat \theta}$ over the class of H\"olderian functions and we prove the optimality of this bound up to a logarithmic factor. Finally, we provide an algorithm for calculating $\boldsymbol{\widehat \theta}$ when $\boldsymbol{\theta}^{\star}$ is assumed to belong to functional classes of low or medium dimensions (in a suitable sense) and, on a simulation study, we compare the performance of $\boldsymbol{\widehat \theta}$ to that of the MLE and median-based estimators. The proof of our main result relies on an upper bound, with explicit numerical constants, on the expectation of the supremum of an empirical process over a VC-subgraph class. This bound can be of independent interest.

We provide convergence guarantees for the Deep Ritz Method for abstract variational energies. Our results cover non-linear variational problems such as the $p$-Laplace equation or the Modica-Mortola energy with essential or natural boundary conditions. Under additional assumptions, we show that the convergence is uniform across % bounded families of right-hand sides.

We investigate non-adaptive methods of deep ReLU neural network approximation of the solution $u$ to parametric and stochastic elliptic PDEs with lognormal inputs on non-compact set $\mathbb{R}^\infty$. The approximation error is measured in the norm of the Bochner space $L_2(\mathbb{R}^\infty, V, \gamma)$, where $\gamma$ is the tensor product standard Gaussian probability on $\mathbb{R}^\infty$ and $V$ is the energy space. The approximation is based on an $m$-term truncation of the Hermite generalized polynomial chaos expansion (gpc) of $u$. Under a certain assumption on $\ell_q$-summability condition for lognormal inputs ($0< q <\infty$), we proved that for every integer $n > 1$, one can construct a non-adaptive compactly supported deep ReLU neural network $\boldsymbol{\phi}_n$ of size not greater than $n$ on $\mathbb{R}^m$ with $m = \mathcal{O} (n/\log n)$, having $m$ outputs so that the summation constituted by replacing polynomials in the $m$-term truncation of Hermite gpc expansion by these $m$ outputs approximates $u$ with an error bound $\mathcal{O}\left(\left(n/\log n\right)^{-1/q}\right)$. This error bound is comparable to the error bound of the best approximation of $u$ by $n$-term truncations of Hermite gpc expansion which is $\mathcal{O}(n^{-1/q})$. We also obtained some results on similar problems for parametric and stochastic elliptic PDEs with affine inputs, based on the Jacobi and Taylor gpc expansions.

We study linear stability of solutions to the Navier\textendash Stokes equations with stochastic viscosity. Specifically, we assume that the viscosity is given in the form of a~stochastic expansion. Stability analysis requires a solution of the steady-state Navier-Stokes equation and then leads to a generalized eigenvalue problem, from which we wish to characterize the real part of the rightmost eigenvalue. While this can be achieved by Monte Carlo simulation, due to its computational cost we study three surrogates based on generalized polynomial chaos, Gaussian process regression and a shallow neural network. The results of linear stability analysis assessment obtained by the surrogates are compared to that of Monte Carlo simulation using a set of numerical experiments.

We introduce a new $\mathbf F$-modulated energy stability framework for general linear multistep methods. We showcase the theory for the two dimensional molecular beam epitaxy model with no slope selection which is a prototypical gradient flow with Lipschitz-bounded nonlinearity. We employ a class of representative BDF$k$, $2\le k \le 5$ discretization schemes with explicit $k^{\mathrm{th}}$-order extrapolation of the nonlinear term. We prove the uniform-in-time boundedness of high Sobolev norms of the numerical solution. The upper bound is unconditional, i.e. regardless of the size of the time step. We develop a new algebraic theory and calibrate nearly optimal and \emph{explicit} maximal time step constraints which guarantee monotonic $\mathbf F$-modulated energy dissipation.

Our objective is to stabilise and accelerate the time-domain boundary element method (TDBEM) for the three-dimensional wave equation. To overcome the potential time instability, we considered using the Burton--Miller-type boundary integral equation (BMBIE) instead of the ordinary boundary integral equation (OBIE), which consists of the single- and double-layer potentials. In addition, we introduced a smooth temporal basis, i.e. the B-spline temporal basis of order $d$, whereas $d=1$ was used together with the OBIE in a previous study [Takahashi 2014]. Corresponding to these new techniques, we generalised the interpolation-based fast multipole method that was developed in \cite{takahashi2014}. In particular, we constructed the multipole-to-local formula (M2L) so that even for $d\ge 2$ we can maintain the computational complexity of the entire algorithm, i.e. $O(N_{\rm s}^{1+\delta} N_{\rm t})$, where $N_{\rm s}$ and $N_{\rm t}$ denote the number of boundary elements and the number of time steps, respectively, and $\delta$ is theoretically estimated as $1/3$ or $1/2$. The numerical examples indicated that the BMBIE is indispensable for solving the homogeneous Dirichlet problem, but the order $d$ cannot exceed 1 owing to the doubtful cancellation of significant digits when calculating the corresponding layer potentials. In regard to the homogeneous Neumann problem, the previous TDBEM based on the OBIE with $d=1$ can be unstable, whereas it was found that the BMBIE with $d=2$ can be stable and accurate. The present study will enhance the usefulness of the TDBEM for 3D scalar wave problems.

High-index saddle dynamics provides an effective means to compute the any-index saddle points and construct the solution landscape. In this paper we prove the optimal-order error estimates for Euler discretization of high-index saddle dynamics with respect to the time step size, which remains untreated in the literature. We overcome the main difficulties that lie in the strong nonlinearity of the saddle dynamics and the orthonormalization procedure in the numerical scheme that is uncommon in standard discretization of differential equations. The derived methods are further extended to study the generalized high-index saddle dynamics for non-gradient systems and provide theoretical support for the accuracy of numerical implementations.

In this work, we propose three novel block-structured multigrid relaxation schemes based on distributive relaxation, Braess-Sarazin relaxation, and Uzawa relaxation, for solving the Stokes equations discretized by the mark-and-cell scheme. In our earlier work \cite{he2018local}, we discussed these three types of relaxation schemes, where the weighted Jacobi iteration is used for inventing the Laplacian involved in the Stokes equations. In \cite{he2018local}, we show that the optimal smoothing factor is $\frac{3}{5}$ for distributive weighted-Jacobi relaxation and inexact Braess-Sarazin relaxation, and is $\sqrt{\frac{3}{5}}$ for $\sigma$-Uzawa relaxation. Here, we propose mass-based approximation inside of these three relaxations, where mass matrix $Q$ obtained from bilinear finite element method is directly used to approximate to the inverse of scalar Laplacian operator instead of using Jacobi iteration. Using local Fourier analysis, we theoretically derive the optimal smoothing factors for the resulting three relaxation schemes. Specifically, mass-based distributive relaxation, mass-based Braess-Sarazin relaxation, and mass-based $\sigma$-Uzawa relaxation have optimal smoothing factor $\frac{1}{3}$, $\frac{1}{3}$ and $\sqrt{\frac{1}{3}}$, respectively. Note that the mass-based relaxation schemes do not cost more than the original ones using Jacobi iteration. Another superiority is that there is no need to compute the inverse of a matrix. These new relaxation schemes are appealing.