{"paper_id":"2509.20239","title":"Error Propagation in Dynamic Programming: From Stochastic Control to Option Pricing","authors":["Andrea Della Vecchia","Damir Filipović"],"paper_date":"2025-09-24","paper_type":"theoretical","paper_url":"https://arxiv.org/pdf/2509.20239v1","page_url":"https://thequant.space/flowcharts/error-propagation-in-dynamic-programming-from-stochastic-co/","scores":{"empirical_rigor":6,"math_complexity":8.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a general RKHS-based formulation of approximate dynamic programming through backward induction.","quote":"First, we propose a general RKHS-based formulation of approximate dynamic programming through backward induction.","summary":"This paper investigates theoretical and methodological foundations for stochastic optimal control (SOC) in discrete time. We start formulating the control problem in a general dynamic programming framework, introducing the mathematical structure needed for a detailed convergence analysis. The…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Square integrability of the transition and reward functions with constants cF>0 and cP>0.","type":"statistical","stated":"explicit","quote":"Assumption 1 (Square integrability). There exist constants cF > 0 and cP > 0 such that, for all t ∈{0, . . . , T}: …"},{"assumption":"Source condition: the target regression function lies in the range of Lk^{βt/2} for some βt∈(0,1].","type":"model","stated":"explicit","quote":"Assumption 3 (Source Condition). There exists βt ∈(0, 1] such that W* t ∈Lβt/2 k (L2 µt), where Lk : L2 µt →L2 µt is the integral operator associated with the kernel k."}]},"datasets":{"status":"available","items":[{"name":"Max-Call option benchmark (Goudenege et al., 2020 Table 3)","provider":null,"kind":"synthetic","access":"public","period":null,"universe":null,"quote":"We primarily compare our results with the numerical benchmarks reported in Goudenege et al. (2020). Specifically, we replicate the results in their Table 1 and Table 3, which correspond to pricing a geometric basket put option and a max-call option, respectively."},{"name":"Geometric basket put option benchmark (Goudenege et al., 2020 Table 1)","provider":null,"kind":"synthetic","access":"public","period":null,"universe":null,"quote":"We primarily compare our results with the numerical benchmarks reported in Goudenege et al. (2020). Specifically, we replicate the results in their Table 1 and Table 3, which correspond to pricing a geometric basket put option and a max-call option, respectively."}],"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 proposed KRR-DP algorithm achieves pricing results comparable to benchmark methods while being computationally efficient.","kind":"performance","quote":"The results show that our method performs competitively with existing algorithms, offering a favorable trade-off between accuracy and computational efficiency."},{"finding":"The framework provides rigorous theoretical guarantees, including explicit error bounds for the value function estimator.","kind":"theoretical","quote":"The framework is supported by rigorous theoretical guarantees, including explicit error bounds."}],"reported_performance":null,"out_of_sample":{"method":"none","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":20,"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":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":"2026-11-14T17:26:18Z"},"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/"}