paper-with-me

Papers

Machine learning approximation algorithms for high-dimensional fully nonlinear partial differential equations and second-order backward stochastic differential equations

2017-09-18 · Christian Beck, Weinan E, Arnulf Jentzen

High-dimensional partial differential equations (PDE) appear in a number of models from the financial industry, such as in derivative pricing models, credit valuation adjustment (CVA) models, or portfolio optimization models. The PDEs in such applications are high-dimensional as the dimension corresponds to the number of financial assets in a portfolio. Moreover, such PDEs are often fully nonlinear due to the need to incorporate certain nonlinear phenomena in the model such as default risks, transaction costs, volatility uncertainty (Knightian uncertainty), or trading constraints in the model. Such high-dimensional fully nonlinear PDEs are exceedingly difficult to solve as the computational effort for standard approximation methods grows exponentially with the dimension. In this work we propose a new method for solving high-dimensional fully nonlinear second-order PDEs. Our method can in particular be used to sample from high-dimensional nonlinear expectations. The method is based on (i) a connection between fully nonlinear second-order PDEs and second-order backward stochastic differential equations (2BSDEs), (ii) a merged formulation of the PDE and the 2BSDE problem, (iii) a temporal forward discretization of the 2BSDE and a spatial approximation via deep neural nets, and (iv) a stochastic gradient descent-type optimization procedure. Numerical results obtained using ${\rm T{\small ENSOR}F{\small LOW}}$ in ${\rm P{\small YTHON}}$ illustrate the efficiency and the accuracy of the method in the cases of a $100$-dimensional Black-Scholes-Barenblatt equation, a $100$-dimensional Hamilton-Jacobi-Bellman equation, and a nonlinear expectation of a $ 100 $-dimensional $ G $-Brownian motion.

📄 PDF Abstract BibTeX arXiv:1709.05963

Code (0)

등록된 구현이 없습니다.

Tasks

Portfolio Optimization

Similar Papers 제목 키워드 기반

Deep Networks as Denoising Algorithms: Sample-Efficient Learning of Diffusion Models in High-Dimensional Graphical Models

2023-09-20 · Song Mei, Yuchen Wu

We investigate the approximation efficiency of score functions by deep neural networks in diffusion-based generative modeling. While existing approximation theories utilize the smoothness of score functions, they suffer …

DenoisingEfficient Neural NetworkVariational Inference

On efficient algorithms for computing near-best polynomial approximations to high-dimensional, Hilbert-valued functions from limited samples

2022-03-25 · Ben Adcock, Simone Brugiapaglia, Nick Dexter, Sebastian Moraga

Sparse polynomial approximation has become indispensable for approximating smooth, high- or infinite-dimensional functions from limited samples. This is a key task in computational science and engineering, e.g., surrogat…

compressed sensingUncertainty Quantification

Physics-Informed Neural Network Policy Iteration: Algorithms, Convergence, and Verification

2024-02-15 · Yiming Meng, Ruikun Zhou, Amartya Mukherjee, Maxwell Fitzsimmons 외

Solving nonlinear optimal control problems is a challenging task, particularly for high-dimensional problems. We propose algorithms for model-based policy iterations to solve nonlinear optimal control problems with conve…

Rank-R FNN: A Tensor-Based Learning Model for High-Order Data Classification

2021-04-11 · Konstantinos Makantasis, Alexandros Georgogiannis, Athanasios Voulodimos, Ioannis Georgoulas 외

An increasing number of emerging applications in data science and engineering are based on multidimensional and structurally rich data. The irregularities, however, of high-dimensional data often compromise the effective…

BIG-bench Machine LearningGeneral Classification

Rough extreme learning machine: a new classification method based on uncertainty measure

2017-10-30 · Lin Feng, Shuliang Xu, Feilong Wang, Shenglan Liu

Extreme learning machine (ELM) is a new single hidden layer feedback neural network. The weights of the input layer and the biases of neurons in hidden layer are randomly generated, the weights of the output layer can be…

AttributeGeneral Classification