Learning parameter dependence for Fourier-based option pricing with tensor trains
By Rihito Sakurai, Haruto Takahashi, Koichi Miyamoto
Rating
1749
Battle Count: 78
Relevance
8/10
Highly relevant for fast multi-asset option pricing, which is crucial in quantitative trading strategies involving options
Implementation Complexity
7/10
Requires understanding of tensor networks and Fourier transform methods, but builds on existing algorithms
Reproducibility
4/5
Detailed methodology and parameter settings provided, but code not explicitly shared
About this paper
Methodology: Tensor Train Learning. Problem types: Option Pricing, Dimensionality Reduction.
The interactive Everscope explorer (charts, battles, favorites) loads below.