The Deep Penalty Method approximates penalized PDEs for optimal stopping via Deep BSDE, with error bounded by training loss plus O(1/λ) + O(λ h) + O(√h), and shows accuracy on high-dimensional American option pricing.
(2015): Stochastic control representations for penalized backward stochastic differential equations, SIAM Journal on Control and Optimization, 53, 1440--1463
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
q-fin.MF 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Deep Penalty Methods: A Class of Deep Learning Algorithms for Solving High Dimensional Optimal Stopping Problems
The Deep Penalty Method approximates penalized PDEs for optimal stopping via Deep BSDE, with error bounded by training loss plus O(1/λ) + O(λ h) + O(√h), and shows accuracy on high-dimensional American option pricing.