{"paper_id":"2409.06551","title":"Robust financial calibration: a Bayesian approach for neural SDEs","authors":["Christa Cuchiero","Eva Flonner","Kevin Kurt"],"paper_date":"2024-09-10","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2409.06551v4","page_url":"https://thequant.space/flowcharts/robust-financial-calibration-a-bayesian-approach-for-neural/","scores":{"empirical_rigor":4,"math_complexity":9,"quadrant":"Lab Rats"},"proposes":{"status":"available","statement":"The paper proposes a Bayesian calibration framework for neural stochastic differential equations that jointly calibrates to option and time series data.","quote":"the goal of the current paper is to unite the efforts described above and provide a Bayesian calibration framework based on neural SDEs.","summary":"The paper presents a Bayesian framework for the calibration of financial models using neural stochastic differential equations (neural SDEs), for which we also formulate a global universal approximation theorem based on Barron-type estimates. The method is based on the specification of a prior…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Risk‑free rate is set to zero for simplicity.","type":"market","stated":"explicit","quote":"From now on we assume for notational simplicity that r = 0, unless specified otherwise."},{"assumption":"Option market price equals model price plus normally distributed noise.","type":"statistical","stated":"explicit","quote":"the basis point calibration error for the ith option for the true, underlying θ is supposed to be normally distributed as 104 S0 (C(i)mod(θ) −C(i)mkt) ∼N(0, δ2 i )."},{"assumption":"Prior distribution is placed on neural network weights.","type":"model","stated":"explicit","quote":"Together with a prior distribution p(θ) on the weights θ of the neural networks (σ, bV , σV ) appearing in the neural SDE system (1),(2), the desired posterior distribution will then be obtained explicitly."},{"assumption":"Hedging instruments are square‑integrable martingales under the risk‑neutral measure.","type":"model","stated":"explicit","quote":"consider p traded hedging instruments (Zt)t∈[0,T ] (including in particular the traded assets Sθ) which are square integrable martingales under the risk neutral measure Q(θ) and take values in Rp."},{"assumption":"Synthetic historical data follows a geometric Brownian motion with drift 0.05 and diffusion 0.3.","type":"data","stated":"explicit","quote":"The input data for the historical measure is one trajectory from the logarithm of a geometric Brownian motion with drift 0.05 and diffusion 0.3. dYt = (0.05 −0.5 · 0.32)dt + 0.3dWt, Y0 = 0 simulated via the Euler‑Maruyama scheme."},{"assumption":"Option data are Black‑Scholes call prices for specified strikes and maturities.","type":"data","stated":"explicit","quote":"The input for the Q‑measure are call option prices obtained from the Black Scholes formula for risk‑free rate r = 0.025, 21 strikes from 0.8 to 1.2 and maturities 16, 32, 48, 64, 80 and 96."}]},"datasets":{"status":"available","items":[{"name":"Synthetic GBM trajectory","provider":null,"kind":"synthetic","access":"unknown","period":null,"universe":null,"quote":"The input data for the historical measure is one trajectory from the logarithm of a geometric Brownian motion with drift 0.05 and diffusion 0.3."},{"name":"Black‑Scholes call option prices","provider":"Black‑Scholes formula","kind":"options","access":"public","period":null,"universe":null,"quote":"The input for the Q‑measure are call option prices obtained from the Black Scholes formula for risk‑free rate r = 0.025, 21 strikes from 0.8 to 1.2 and maturities 16, 32, 48, 64, 80 and 96."},{"name":"S&P 500 implied volatility data (1990s)","provider":null,"kind":"options","access":"public","period":"1990s","universe":"S&P 500","quote":"... is calibrated to real call options considering empirical S&P 500 implied volatility data with 10 strikes and 4 maturities."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"unclear"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R3","candidates":{"front_matter":"n/a","evidence_card":"n/a","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"pricing-calibration","findings":[{"finding":"The posterior distribution provides robust bounds on implied volatility surfaces and exotic option prices.","kind":"pricing-calibration","quote":"the model naturally produces a distribution on prices for exotic options, by computing the variance‑reduced Monte Carlo prices of these exotics using the calibrated neural SDE model and Langevin sampling."},{"finding":"Algorithm converged around epoch 13, after which draws are from the posterior.","kind":"performance","quote":"The trace plots reveal that the algorithm converged around epoch 13. This means that after this epoch we are dealing with approximate draws from the posterior distribution."},{"finding":"Calibration is not very sensitive to the bid‑ask spread parameter δ.","kind":"statistical","quote":"The results reveal that the calibration to option data, as well as time series data, is not very sensitive with respect to changes in δ."},{"finding":"Neural SDE learns the statistical properties of the Heston model, including mean‑reversion in spot variance.","kind":"theoretical","quote":"Our comparison aims to evaluate to which extent the neural SDE is capable of replicating the typical characteristics of the Heston model such as mean‑reversion in the spot variance."},{"finding":"Smaller prior variance σprior yields more stable calibration results.","kind":"statistical","quote":"Numerical experiments have shown that smaller values of σprior yield more stable results."}],"reported_performance":null,"out_of_sample":{"method":"none","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":35,"citations":{"cited_by_in_corpus":0,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":0},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":true,"code_url":"https://github.com/evaflonner/Calibration-of-Neural-SDEs-using-Bayesian-Methods","note":null},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":1,"extracted_at":"2026-11-14T18:02:45Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}