Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 4
Encontrada(s) 1 página(s)

RUC. Repositorio da Universidade da Coruña
Publicación Tesis doctoral (DoctoralThesis)

Solution of High-Dimensional Nonlinear Parabolic PDEs by Means of High-Order IMEX Local Discontinuous Galerkin Methods (LDG) and Neural Networks (PINNs). Applications in Finance

  • Pérez Villarino, Joel
[Abstract] This dissertation presents two complementary research contributions to the numerical solution of problems in counterparty credit risk. First, we develop high-order local discontinuous Galerkin (LDG) numerical methods with implicit-explicit (IMEX) time marching for solving high-dimensional nonlinear parabolic partial differential equations (PDEs), detailing the space–time discretization, algebraic structure, and sparse-grid strategies for mitigating the curse of dimensionality. Second, we apply deep learning to high-dimensional tasks: (i) boundary-safe physics-informed neural networks (PINNs) to stabilize the training and improve accuracy for nonlinear parabolic PDEs relevant to valuation adjustments; and (ii) a cost-effective multi-output architecture to approximate dynamic Initial Margin (DIM) from single-path Monte Carlo-like labels, parameterized by initial market states. Together, these contributions show how LDG and deep learning can be combined to improve robustness and efficiency in valuation frameworks., [Resumen] Esta tesis presenta dos contribuciones complementarias para la resolución numérica de problemas en riesgo de crédito de contraparte. En primer lugar, se desarrollan métodos numéricos de alto orden de tipo local discontinuous Galerkin (LDG) con integración temporal implícito–explícita (IMEX) para ecuaciones en derivadas parciales (EDPs) parabólicas no lineales en alta dimensión, detallando la discretización espacio–temporal, la estructura algebraica resultante y el uso de mallas (sparse) para mitigar la maldición de la dimensión. En segundo lugar, se aplican técnicas de aprendizaje profundo a problemas de alta dimensión: (i) physics-informed neural networks (PINNs) con formulación boundary-safe para estabilizar el entrenamiento y mejorar la precisión en EDPs parabólicas no lineales relevantes en los ajustes de valoración; y (ii) una arquitectura multi-salida eficiente para aproximar el dynamic Initial Margin (DIM) mediante etiquetas generadas a partir de una única trayectoria de Monte Carlo, parametrizadas por los estados iniciales de mercado. Conjuntamente, estas aportaciones muestran cómo LDG y el aprendizaje profundo se combinan para mejorar la robustez y la eficiencia en contextos de valoración., [Resumo] Esta tese presenta dúas contribucións complementarias para a resolución numérica de problemas en risco de crédito de contraparte. En primeiro lugar, desenvólvense métodos numéricos de alta orde de tipo local discontinuous Galerkin (LDG) con integración temporal implícito-explícita (IMEX) para ecuacións en derivadas parciais (EDPs) parabólicas no lineais en alta dimensión, detallando a discretización espazo-temporal, a estrutura alxebraica e o uso de grellas sparse para mitigar a maldición da dimensión. En segundo lugar, aplícanse técnicas de aprendizaxe profunda a problemas de alta dimensión: (i) physics-informed neural networks (PINNs) con formulación boundary-safe para estabilizar o adestramento e mellorar a precisión en EDPs parabólicas no lineais relevantes para os axustes de valoración; e (ii) unha arquitectura multi-saída eficiente para aproximar o dynamic Initial Margin (DIM) mediante etiquetas xeradas a partir de unha única traxectoria de Monte Carlo, parametrizadas polos estados iniciais de mercado. Conxuntamente, estas aportacións mostran cómo LDG e a aprendizaxe profunda se combinan para mellorar a robustez e a eficiencia en contextos de valoración., Funding This research has been partially funded by: • Xunta de Galicia (European Regional Development Fund, Galicia 2021-2027 Program) through the grant ED481A/2023-2026. • Spanish Ministry of Science and Innovation through the research project PDI2019-108584RB-I00, including FEDER financial support. • Spanish Ministry of Science and Innovation through the research project PID2022-141058OB-I00, including FEDER financial support. • Xunta de Galicia (European Regional Development Fund, Galicia 2014-2020 Program) through the grant ED431C 2018/33, including FEDER financial support. • Xunta de Galicia (European Regional Development Fund, Galicia 2021-2027 Program) through the grant ED431C 2022/47, including FEDER financial support. • Xunta de Galicia (European Regional Development Fund, Galicia 2014-2020 Program) through the grant ED431G 2019/01 obtained by Centro de Investigación en Tecnologías de la Información y las Comunicaciones de Galicia, CITIC, including FEDER financial support. • Xunta de Galicia (European Regional Development Fund, Galicia 2021-2027 Program) through the grant ED431G 2023/01, obtained by CITIC, as a center accredited for excellence within the Galician University System and a member of the CIGUS Network, including FEDER financial support. • CARDAMOM team (Certified Adaptive discrete models for robust simulations of complex flows with moving fronts) at the Inria Centre of the University of Bordeaux., Xunta de Galicia; ED481A/2023-2026, Xunta de Galicia; ED431C 2018/33, Xunta de Galicia; ED431C 2022/47, Xunta de Galicia; ED431G 2019/01, Xunta de Galicia; ED431G 2023/01
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Model and numerical methods for pricing renewable energy certificate derivatives

  • Baamonde-Seoane, María A.
  • Calvo-Garrido, María-del-Carmen
  • Vázquez, Carlos
[Abstract]: Assuming that the price of the renewable energy certificate (REC) is known, we formulate the valuation problem of a European REC derivative in terms of a linear PDE model where the underlying stochastic factors are the accumulated green certificates sold by an authorized producer and the natural logarithm of the renewable generation rate. Next, a result of existence of solution is obtained for this PDE problem. In order to solve numerically the PDE problem, we propose two different methods: a semi-Lagrangian scheme in time combined with finite differences discretizations in the spatial-like variables, or alternative Lagrange–Galerkin methods. The application to the pricing of European options and futures on renewable energy certificates is addressed. Finally, we show illustrative results about the performance of the models and numerical methods that have been implemented., Xunta de Galicia; ED431C 2018/033, Xunta de Galicia; ED431C 2022/047, Xunta de Galicia; ED431G 2019/01, This work has been funded by MICINN from Spain (Grant PID2019-10858RB-I00), and by Xunta of Galicia (Grant ED431C 2018/033 and ED431C 2022/047), all including FEDER financial co-funding. All authors are members of CITIC, so that they acknowledge grant ED431G 2019/01, funded by Consellería de Educación, Universidade e Formación Profesional of Xunta de Galicia through FEDER, Spain funds with 80%, from FEDER Galicia 2014–2020 Program and 20% from Secretaría Xeral de Universidades. Funding for open access charge: Universidade da Coruña/CISUG. Authors are also grateful to two anonymous reviewers whose remarks helped to improve the article.
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Boundary-safe PINNs extension: Application to non-linear parabolic PDEs in counterparty credit risk

  • Pérez Villarino, Joel
  • Leitao, Álvaro
  • García Rodríguez, José Antonio
[Abstract]: The goal of this work is to develop a novel strategy for the treatment of the boundary conditions for multi-dimension nonlinear parabolic PDEs. The proposed methodology allows to get rid of the heuristic choice of the weights for the different addends that appear in the loss function related to the training process. It is based on defining the losses associated to the boundaries by means of the PDEs that arise from substituting the related conditions into the model equation itself. The approach is applied to challenging problems appearing in quantitative finance, namely, in counterparty credit risk management. Further, automatic differentiation is employed to obtain accurate approximation of the partial derivatives, the so called Greeks, that are very relevant quantities in the field., Xunta de Galicia; ED431C 2018/33, Xunta de Galicia; ED431G 2019/01, A.L and J.A.G.R. acknowledge the support received by the Spanish MINECO under research project number PDI2019-108584RB-I00, and by the Xunta de Galicia, Spain under grant ED431C 2018/33. All the authors thank to the support received from the CITIC research center, funded by Xunta de Galicia and the European Union (European Regional Development Fund - Galicia Program, Spain ), by grant ED431G 2019/01.
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Pricing renewable energy certificates with a Crank–Nicolson Lagrange–Galerkin numerical method

  • Baamonde-Seoane, María A.
  • Calvo-Garrido, María-del-Carmen
  • Vázquez, Carlos
Financiado para publicación en acceso aberto: Universidade da Coruña/CISUG, [Abstract]: The valuation problem of renewable energy certificates can be formulated in terms of a nonlinear PDE model where the underlying stochastic factors are the accumulated green certificates sold by an authorized producer and the natural logarithm of the renewable generation rate. In the present paper, the nonlinear convective term is treated with the Bermúdez–Moreno duality method for maximal monotone operators as in Baamonde-Seoane et al. (2021). The main novelty of this article comes from the proposed techniques for the numerical solution of the resulting linear problem. In this case, we propose a Lagrange–Galerkin method which mainly consists of Crank–Nicolson characteristics for time discretization combined with finite elements for the discretization in the accumulated green certificates and the natural logarithm of the renewable generation rate directions. Finally, several numerical examples are presented to illustrate the good performance of the method and model, and its comparison with other numerical schemes employed to solve the same problem., Xunta de Galicia; ED431C 2018/033, Xunta de Galicia; ED431C 2022/47, Xunta de Galicia; ED431G 2019/01, The authors acknowledge the funding by Spanish MINECO with the grants MTM2016-76497-R and PID2019-10858RB-I00, and by Galician Government, Spain with the grants ED431C 2018/033 and ED431C 2022/47, both including FEDER financial support. As members of CITIC, they also acknowledge the grant ED431G 2019/01, funded by Consellería de Educación, Spain , Universidade e Formación Profesional of Xunta de Galicia through FEDER funds with 80%, from FEDER Galicia 2014–2020 Program and 20% from Secretaría Xeral de Universidades.