Bayesian neural SDE calibration produces posterior mixtures that deliver robust bounds on implied volatility by jointly using historical and option data, learning the historical-to-risk-neutral measure change, and sampling via Langevin dynamics.
Modeling and implementation of local volatility surfaces in Bayesian framework
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
q-fin.CP 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Robust financial calibration: a Bayesian approach for neural SDEs
Bayesian neural SDE calibration produces posterior mixtures that deliver robust bounds on implied volatility by jointly using historical and option data, learning the historical-to-risk-neutral measure change, and sampling via Langevin dynamics.