An Explicit Scheme for Pathwise XVA Computations (2401.13314v1)
Abstract: Motivated by the equations of cross valuation adjustments (XVAs) in the realistic case where capital is deemed fungible as a source of funding for variation margin, we introduce a simulation/regression scheme for a class of anticipated BSDEs, where the coefficient entails a conditional expected shortfall of the martingale part of the solution. The scheme is explicit in time and uses neural network least-squares and quantile regressions for the embedded conditional expectations and expected shortfall computations. An a posteriori Monte Carlo validation procedure allows assessing the regression error of the scheme at each time step. The superiority of this scheme with respect to Picard iterations is illustrated in a high-dimensional and hybrid market/default risks XVA use-case.
- Pathwise CVA regressions with oversimulated defaults. Mathematical Finance 33(2), 274–307.
- XVA Principles, Nested Monte Carlo Strategies, and GPU Optimizations. International Journal of Theoretical and Applied Finance 21, 1850030.
- Numerical approximations of McKean anticipative backward stochastic differential equations arising in initial margin requirements. ESAIM: Proceedings and Surveys 65, 1–26.
- Credit, funding, margin, and capital valuation adjustments for bilateral portfolios. Probability, Uncertainty and Quantitative Risk 2(7), 26 pages.
- XVA analysis from the balance sheet. Quantitative Finance 21(1), 99–123.
- Stochastic approximation schemes for economic capital and risk margin computations. ESAIM: Proceedings and Surveys 65, 182–218.
- Learning the value-at-risk and expected shortfall. arXiv:2209.06476.
- Automatic differentiation in machine learning: a survey. Journal of Marchine Learning Research 18, 1–43.
- Crépey, S. (2022). Positive XVAs. Frontiers of Mathematical Finance 1(3), 425–465.
- When capital is a funding source: The anticipated backward stochastic differential equations of X-Value Adjustments. SIAM Journal on Financial Mathematics 11(1), 99–130.
- BSDEs of counterparty risk. Stochastic Processes and their Applications 125(8), 3023–3052.
- Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations. Communications in Mathematics and Statistics 5(4), 370–398.
- Deep xVA solver–a neural network based counterparty credit risk management framework. arXiv:2005.02633.
- Gobet, E. (2016). Monte-Carlo methods and stochastic processes: from linear to non-linear. Chapman and Hall/CRC.
- Deep Learning. MIT Press. http://www.deeplearningbook.org.
- Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In Proceedings of the IEEE international conference on computer vision, pp. 1026–1034.
- Semimartingale Theory and Stochastic Calculus. Science Press and CRC Press Inc.
- Henry-Labordère, P. (2019). CVA and IM: welcome to the machine. Risk Magazine, March. In preprint form: ssrn.3071506.
- Deep backward schemes for high-dimensional nonlinear PDEs. Mathematics of Computation 89(324), 1547–1579.
- Jacod, J. and A. N. Shiryaev (2003). Limit Theorems for Stochastic Processes (2nd ed.). Springer.
- Adam: A method for stochastic optimization. arXiv:1412.6980.
- Anticipated backward stochastic differential equations. The Annals of Probability 37(3), 877–902.
- Savine, A. (2018). Modern computational finance: AAD and parallel simulations. John Wiley & Sons.