Deep Penalty Methods: A Class of Deep Learning Algorithms for Solving High Dimensional Optimal Stopping Problems
By Yunfei Peng, Pengyu Wei, Wei Wei
Rating
1869
Battle Count: 134
Relevance
8/10
Highly relevant for pricing complex derivatives and solving high-dimensional optimal stopping problems in quantitative finance
Implementation Complexity
7/10
Requires deep learning expertise and understanding of stochastic processes, but builds on existing Deep BSDE framework
Reproducibility
4/5
The paper provides detailed algorithm description and error analysis, but lacks specific hyperparameters for full reproduction
About this paper
Methodology: Deep Penalty Method (DPM). Problem types: Optimal Stopping, High-Dimensional PDEs, American Option Pricing.
The interactive Everscope explorer (charts, battles, favorites) loads below.