Derives computable a posteriori error bounds for decoupled neural approximations of fully coupled FBSDEs that depend on terminal defect, pathwise residual, and control mismatch, backed by continuous-time stability estimates and numerical tests.
Deep Neural Networks Algorithms for Stochastic Control Problems on Finite Horizon: Convergence Analysis
2 Pith papers cite this work, alongside 95 external citations. Polarity classification is still indexing.
2
Pith papers citing it
95
external citations · OpenAlex
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
A deep learning dynamic programming scheme prices path-dependent convertible bonds under GBM, CEV and Heston dynamics, showing that reset and call clauses dominate the underlying process in determining value and that downward resets can paradoxically lower bond prices.
citing papers explorer
-
A Posteriori Error Analysis for Decoupled Neural Approximations of Fully Coupled FBSDEs with Control Mismatch
Derives computable a posteriori error bounds for decoupled neural approximations of fully coupled FBSDEs that depend on terminal defect, pathwise residual, and control mismatch, backed by continuous-time stability estimates and numerical tests.
-
A deep learning approach for pricing convertible bonds with path-dependent reset and call provisions
A deep learning dynamic programming scheme prices path-dependent convertible bonds under GBM, CEV and Heston dynamics, showing that reset and call clauses dominate the underlying process in determining value and that downward resets can paradoxically lower bond prices.