Latent Flow Matching for Arbitrage-Aware Implied Volatility Surface Generation

Dusica Bajalica (), Oscar Brooks (), Imen Tahar and Yating Liu ()
Additional contact information
Dusica Bajalica: Université Paris Dauphine-PSL - PSL - Université Paris Sciences et Lettres
Oscar Brooks: Université Paris Dauphine-PSL - PSL - Université Paris Sciences et Lettres, NYU - New York University [New York] - NYU - NYU System
Imen Tahar: CEREMADE - CEntre de REcherches en MAthématiques de la DEcision - Université Paris Dauphine-PSL - PSL - Université Paris Sciences et Lettres - CNRS - Centre National de la Recherche Scientifique, Université Paris Dauphine-PSL - PSL - Université Paris Sciences et Lettres
Yating Liu: CEREMADE - CEntre de REcherches en MAthématiques de la DEcision - Université Paris Dauphine-PSL - PSL - Université Paris Sciences et Lettres - CNRS - Centre National de la Recherche Scientifique, Université Paris Dauphine-PSL - PSL - Université Paris Sciences et Lettres

Post-Print from HAL

Abstract: We propose an arbitrage-aware latent flow-matching framework for unconditional implied volatility surface generation. The method first compresses high-dimensional surfaces into a low-dimensional latent space using a variational autoencoder regularized by differentiable calendar-spread, call-spread and butterfly-arbitrage penalties. A flow-matching model then learns to transport a Gaussian prior toward the empirical latent distribution, and generated latent samples are decoded back into volatility surfaces. We evaluate the approach using marginal and surface-level Wasserstein distances, smile and skew diagnostics, pointwise quantile surfaces, financially interpretable shape metrics, and static no-arbitrage tests. The proposed model closely reproduces the empirical distribution and the main maturity-moneyness structures, achieves the best performance in the extreme $Q_{99}$ regime, and generates $90.8\%$ of surfaces satisfying all tested static no-arbitrage conditions. Overall, the results show that latent flow matching provides a favorable balance between distributional similarity, tail preservation, and financial consistency without requiring post-sampling reweighting.

Date: 2026-11-14
New Economics Papers: this item is included in nep-rmg
Note: View the original document on HAL open archive server: https://hal.science/hal-05804110v1
References: Add references at CitEc
Citations:

Published in ICAIF '26 - 7th ACM International Conference on AI in Finance, Nov 2026, Milan, Italy. ⟨10.1145/3858063.3858741⟩

Downloads: (external link)
https://hal.science/hal-05804110v1/document (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hal:journl:hal-05804110

DOI: 10.1145/3858063.3858741

Access Statistics for this paper

More papers in Post-Print from HAL
Bibliographic data for series maintained by CCSD ().