{"paper_id":"2311.07231","title":"Error Analysis of Option Pricing via Deep PDE Solvers: Empirical Study","authors":["Rawin Assabumrungrat","Kentaro Minami","Masanori Hirano"],"paper_date":"2023-11-13","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2311.07231v1","page_url":"https://thequant.space/flowcharts/error-analysis-of-option-pricing-via-deep-pde-solvers-empir/","scores":{"empirical_rigor":8,"math_complexity":7.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper provides practical guidelines and empirical evaluation of deep PDE/BSDE solvers for high‑dimensional option pricing, highlighting error sources and recommending configurations.","quote":"Our primary objective is to provide practical guidelines for the design of models and training algorithms in option pricing using Deep PDE/BSDE solvers.","summary":"Option pricing, a fundamental problem in finance, often requires solving non-linear partial differential equations (PDEs). When dealing with multi-asset options, such as rainbow options, these PDEs become high-dimensional, leading to challenges posed by the curse of dimensionality. While deep…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Option pricing is performed on a high‑dimensional rainbow (best‑of) call option with 20 underlying assets.","type":"model","stated":"explicit","quote":"Our standard setting uses a call, best-of option of N = 20 underlying assets."},{"assumption":"Asset price dynamics follow the specified stochastic model with parameters ρ, κ, ξ, etc., satisfying 2κθ > ξ² to keep variance positive.","type":"model","stated":"explicit","quote":"The values of ρ, κ, and ξ are the default parameters of options provided by [25]"},{"assumption":"Neural network architectures and hyper‑parameters are kept constant across all tested algorithms.","type":"execution","stated":"explicit","quote":"In addition, regarding the standard hyperparameters applied across all tested algorithms, the neural networks have a total of 4…"},{"assumption":"Batch size can be increased arbitrarily (e.g., using GPUs) without affecting computation feasibility.","type":"execution","stated":"implied","quote":"Since there are confirmed advantages to enlarging the batch, it is strongly recommended that batch size in any algorithm is as large as possible. This is especially advised in environments equipped with GPUs where it is unlikely that a larger batch size will hold back computation."}]},"datasets":{"status":"available","items":[{"name":"Synthetic asset price simulations for high‑dimensional rainbow options","provider":null,"kind":"synthetic","access":"unknown","period":null,"universe":"20 underlying assets","quote":"Our standard setting uses a call, best-of option of N = 20 underlying assets."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"synthetic"},"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 Deep BSDE method consistently outperforms other deep PDE solvers and is robust to variations in option parameters such as time to expiration.","kind":"performance","quote":"Our results indicate that the Deep BSDE method (DBSDE) is superior in performance and exhibits robustness against variations in option specifications."},{"finding":"Error decreases proportionally to 1/√batch size and 1/√time steps, aiding computational budgeting for target accuracies.","kind":"performance","quote":"to the square root of the batch size (proportion to 1/√batch size) and the number of time discretization steps (proportion to 1/√time steps)."},{"finding":"Small batch sizes may yield inconsistent price estimates, recommending the use of the largest feasible batch.","kind":"negative","quote":"a small batch size might not fairly reflect the price distribution, which could result in inconsistent estimated option prices."},{"finding":"A strong linear relationship exists between 1/√time steps and error, confirming that finer time discretization reduces pricing error, especially for MDBDP.","kind":"statistical","quote":"There exists a particularly strong linear relationship between 1/√time steps and error."}],"reported_performance":null,"out_of_sample":{"method":"none","headline_out_of_sample":null}},"independent_evidence":{"status":"available","supports":[{"paper":{"paper_id":"2212.12725","title":"Deep Quadratic Hedging","paper_date":"2022-12-24","authors":["Alessandro Gnoatto","Silvia Lavagnini","Athena Picarelli"],"empirical_rigor":5.5,"page_url":"https://thequant.space/flowcharts/deep-quadratic-hedging/"},"question":"How does increasing the number of time steps affect pricing error in deep quadratic hedging and deep PDE solvers?","this_paper_finding":"A strong linear relationship exists between 1/√time steps and error, confirming that finer time discretization reduces pricing error, especially for MDBDP.","other_paper_finding":"Increasing the number of time steps reduces the mean squared error of the option price, though errors accumulate over time.","other_paper_quote":"the MSE is increasing with time. However, we also see a clear improvement when increasing the number of time steps, N.","note":"Both find finer discretization lowers error: A reports reduced MSE with more steps (though errors accumulate), B shows error ∝1/√steps, especially for MDBDP.","confidence":0.826}],"contradicts":[{"paper":{"paper_id":"2505.09459","title":"Monte-Carlo Option Pricing in Quantum Parallel","paper_date":"2025-05-14","authors":["Robert Scriba","Yuying Li","Jingbo B Wang"],"empirical_rigor":2,"page_url":"https://thequant.space/flowcharts/monte-carlo-option-pricing-in-quantum-parallel/"},"question":"How does the number of time steps affect option pricing error in numerical methods?","this_paper_finding":"A strong linear relationship exists between 1/√time steps and error, confirming that finer time discretization reduces pricing error, especially for MDBDP.","other_paper_finding":"Mean pricing error shows little dependence on the number of time steps beyond about 100 steps, where error plateaus.","other_paper_quote":"error begins to plateau at approximately 100 time steps.","note":"A finds error ∝1/√steps (linear with 1/√time steps), B finds error plateaus after ~100 steps, showing little dependence beyond that.","confidence":0.45}],"qualifies":[],"compared_with":38,"citations":{"cited_by_in_corpus":2,"by_independent_authors":1,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":1,"unclassified":1},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":false,"code_url":null,"note":"No repository presented by the authors as their own was found in the paper. Absence here is not proof that no code exists."},"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":"2026-11-14T18:19:38Z"},"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/"}