arXiv releases paper on neural hierarchical factors for derivative pricing
Get up to speed
Aleksandar Arandjelovic and Patrick Cheridito have published a quantitative finance paper on arXiv, proposing a neural network hierarchical factor construction method for derivative pricing under continuous-time models. The study establishes continuity results for conditional expectations and conditional distributions, provides counterexamples to continuity theory, and derives a universal approximation theorem for admissible hierarchical factors by combining neural network density results. Numerical experiments show that the learned hierarchical factors outperform all baselines in two derivative pricing scenarios.
AI-generated from reports · 23 hr agoUpdated
Coverage timeline
Follow the coverage to understand different sides of the event.
- arXiv q-finOn Continuity and Layering of Conditional Distributions for Derivative Pricing
This arXiv quantitative finance paper focuses on constructing neural network layering factors for derivative pricing under continuous-time models. It establishes continuity results for conditional expectations and conditional distributions, provides counterexamples to continuity theory, and derives a universal approximation theorem for admissible layering factors based on neural network density results. Numerical experiments show that the learned layering factors outperform all baselines in two derivative pricing scenarios.
Trend of this event
- Comparable range current
- 5
- Comparable range peak
- 926 Oct 15:00
- Change in last 24 hours
- –
Trend compares only entities observed continuously and completely, so the range may be smaller than the current heat count. Hover or tap the chart for hourly heat; use left/right arrow keys.