English
Related papers

Related papers: Newton-Kantorovitch method for decoupled forward-b…

200 papers

A new decomposition optimization algorithm, called \textit{path-following gradient-based decomposition}, is proposed to solve separable convex optimization problems. Unlike path-following Newton methods considered in the literature, this…

Optimization and Control · Mathematics 2012-09-21 Quoc Tran Dinh , Ion Necoara , Moritz Diehl

Recently, the deep learning method has been used for solving forward-backward stochastic differential equations (FBSDEs) and parabolic partial differential equations (PDEs). It has good accuracy and performance for high-dimensional…

Numerical Analysis · Mathematics 2020-02-04 Shaolin Ji , Shige Peng , Ying Peng , Xichuan Zhang

This paper presents a stochastic block-coordinate proximal Newton method for minimizing the sum of a blockwise Lipschitz-continuously differentiable function and a separable nonsmooth convex function. At each iteration, the method randomly…

Optimization and Control · Mathematics 2026-03-25 Hong Zhu , Xun Qian

In this paper we present two numerical schemes of approximating solutions of backward doubly stochastic differential equations (BDSDEs for short). We give a method to discretize a BDSDE. And we also give the proof of the convergence of…

Probability · Mathematics 2008-06-05 Yufeng Shi , Weiqiang Yang , Jing Yuan

We propose an approach to solve the stochastic neutron point kinetics equations using an adaptation of the diagonalization-decomposition method (DDM). This new approach (Double-DDM) yields a nonstiff solution for the stochastic formulation,…

In this paper, we propose a globally convergent method for solving constrained nonlinear systems. The method combines an efficient Newton conditional gradient method with a derivative-free and nonmonotone linesearch strategy. The global…

Optimization and Control · Mathematics 2018-06-06 M. L. N. Gonçalves , F. R. Oliveira

Newton's method may exhibit slower convergence than vanilla Gradient Descent in its initial phase on strongly convex problems. Classical Newton-type multilevel methods mitigate this but, like Gradient Descent, achieve only linear…

Optimization and Control · Mathematics 2026-02-25 Nick Tsipinakis , Panos Parpas , Matthias Voigt

Newton's method may exhibit slower convergence than vanilla Gradient Descent in its initial phase on strongly convex problems. Classical Newton-type multilevel methods mitigate this but, like Gradient Descent, achieve only linear…

Optimization and Control · Mathematics 2026-03-05 Nick Tsipinakis , Panagiotis Tigkas , Panos Parpas

(Working Paper) Using a purely probabilistic argument, we prove the global well-posedness of multidimensional superquadratic backward stochastic differential equations (BSDEs) without Markovian assumption. The key technique is the interplay…

Probability · Mathematics 2022-01-21 Kihun Nam

We develop a unified Petrov-Galerkin spectral method for a class of fractional partial differential equations with two-sided derivatives and constant coefficients of the form $ _{0}{\mathcal{D}}_{t}^{2\tau}u^{} + \sum_{i=1}^{d}$ $[c_{l_i}$…

Computational Engineering, Finance, and Science · Computer Science 2019-10-02 M. Samiee , M. Zayernouri. Mark M. Meerschaert

We develop a general technique for proving convergence of repeated quantum interactions to the solution of a quantum stochastic differential equation. The wide applicability of the method is illustrated in a variety of examples. Our main…

Mathematical Physics · Physics 2008-10-20 Luc Bouten , Ramon van Handel

The paper considers the numerical solution of nonlinear integral equations using the Newton-Kantorovich method with the mpmath library. High-precision quadrature of the kernel K(t, s, u) with respect to the variable s for fixed t increases…

Numerical Analysis · Mathematics 2025-11-03 Kirill A. Chertoganov , Valery I. Shipalov

In this paper we study the class of backward doubly stochastic differential equations (BDSDEs, for short) whose terminal value depends on the history of forward diffusion. We first establish a probabilistic representation for the spatial…

Probability · Mathematics 2008-11-12 Auguste Aman

We propose a novel framework for solving a class of Partial Integro-Differential Equations (PIDEs) and Forward-Backward Stochastic Differential Equations with Jumps (FBSDEJs) through a deep learning-based approach. This method, termed the…

Numerical Analysis · Mathematics 2024-12-17 Zaijun Ye , Wansheng Wang

By the approximation method introduced in \cite{FYW}, the existence and uniqueness are proved for a class of distribution-dependent stochastic functional differential equations (DDSFDEs). Moreover, combining the Harnack and shift-Harnack…

Probability · Mathematics 2018-01-26 Xing Huang

Derivative boundary conditions introduce challenges for mesh-free discretizations of PDEs on surfaces, especially when the domain is represented by randomly sampled point clouds. The recently developed two-step tangent-space RBF-generated…

Numerical Analysis · Mathematics 2026-03-31 Peng Chen , Shixiao Willing Jiang , Rongji Li , Qile Yan

In this paper we present GSSN, a globalized SCD semismooth* Newton method for solving nonsmooth nonconvex optimization problems. The global convergence properties of the method are ensured by the proximal gradient method, whereas locally…

Optimization and Control · Mathematics 2025-01-27 H. Gfrerer

We introduce a new approach for designing numerical schemes for stochastic differential equations (SDEs). The approach, which we have called direction and norm decomposition method, proposes to approximate the required solution $X_t$ by…

Numerical Analysis · Mathematics 2017-02-21 C. M. Mora , H. A. Mardones , J. C. Jimenez , M. Selva , R. Biscay

We develop a fully discrete, semi-implicit mixed finite element method for approximating solutions to a class of fourth-order stochastic partial differential equations (SPDEs) with non-globally Lipschitz and non-monotone nonlinearities,…

Numerical Analysis · Mathematics 2026-02-17 Beniamin Goldys , Agus L. Soenjaya , Thanh Tran

We present a novel numerical method for solving McKean-Vlasov forward-backward stochastic differential equations (MV-FBSDEs) with common noise, combining Picard iterations, elicitability and deep learning. The key innovation involves…

Machine Learning · Computer Science 2025-12-18 Felipe J. P. Antunes , Yuri F. Saporito , Sebastian Jaimungal