Gaussian process regression can interpolate, with 0.5-3.5% relative error, the mapping from SVI volatility surface parameters to variance swap fair strikes and American put prices and Greeks, yielding 1000x+ inference speedups over finite-difference solvers.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
q-fin.PR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Fast Derivative Valuation from Volatility Surfaces using Machine Learning
Gaussian process regression can interpolate, with 0.5-3.5% relative error, the mapping from SVI volatility surface parameters to variance swap fair strikes and American put prices and Greeks, yielding 1000x+ inference speedups over finite-difference solvers.