Transformer and U-Net models outperform classical SVI parameterization for volatility surface reconstruction from sparse data, with soft arbitrage penalties reducing violations at modest accuracy cost.
Deep smoothing of the implied volatility surface.arXiv preprint arXiv:2004.11015, 2020
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
q-fin.CP 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Volatility Surface Reconstruction using Deep Learning under No-Arbitrage Constraints
Transformer and U-Net models outperform classical SVI parameterization for volatility surface reconstruction from sparse data, with soft arbitrage penalties reducing violations at modest accuracy cost.