{"paper_id":"2309.03966","title":"Fourier Neural Network Approximation of Transition Densities in Finance","authors":["Rong Du","Duy-Minh Dang"],"paper_date":"2023-09-07","paper_type":"theoretical","paper_url":"https://arxiv.org/pdf/2309.03966v3","page_url":"https://thequant.space/flowcharts/fourier-neural-network-approximation-of-transition-densities/","scores":{"empirical_rigor":6.5,"math_complexity":8.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes FourNet, a single‑layer feed‑forward neural network with a Gaussian activation that approximates transition densities using their known characteristic functions.","quote":"This paper introduces FourNet, a novel single-layer feed-forward neural network (FFNN) method designed to approximate transition densities for which closed-form expressions of their Fourier transforms, i.e. characteristic functions, are available.","summary":"This paper introduces FourNet, a novel single-layer feed-forward neural network (FFNN) method designed to approximate transition densities for which closed-form expressions of their Fourier transforms, i.e. characteristic functions, are available. A unique feature of FourNet lies in its use of a…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The parameter space Θ is bounded, implying bounded first derivatives of the learned Fourier transform.","type":"model","stated":"explicit","quote":"Given that Θ is bounded and thus bG(η; θ) possesses a bounded first derivative, the requirement for C′ < ∞ is that G(η) also has a bounded first derivative."},{"assumption":"The random variable associated with the density g(·) is absolutely integrable.","type":"model","stated":"explicit","quote":"This leads us to the assumption that the random variable associated with the density g(·) is absolutely integrable."},{"assumption":"The characteristic function G(·) and its learned counterpart bG(·;θ) are square‑integrable (L2) and integrable (L1) over the Fourier domain.","type":"statistical","stated":"explicit","quote":"Both |Re bG(·; θ)| and |Im bG(·; θ)|, θ ∈Θ, are in L1(R). We also recall that both |ReG(·)| and |ImG(·)| ∈L1(R)"},{"assumption":"The loss function includes an MAE regularization term that controls pointwise loss of non‑negativity.","type":"other","stated":"explicit","quote":"The MAE component enables direct control over the upper bound of the potential pointwise loss of non‑negativity in bg(·; θ)."}]},"datasets":{"status":"available","items":[{"name":"Synthetic transition‑density datasets","provider":null,"kind":"synthetic","access":"unknown","period":null,"universe":null,"quote":"All datasets feature one-dimensional inputs (d = 1), except for the two-dimensional Merton jump-diffusion process discussed in Section 6.3."}],"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":"FourNet can approximate transition densities arbitrarily well in the L2‑sense with a finite number of neurons.","kind":"theoretical","quote":"We mathematically establish FourNet’s capacity to approximate transition densities in the L2-sense arbitrarily well with finite number of neurons."},{"finding":"Training achieves a loss ≤10⁻⁶ and the MAE regularization term is also <10⁻⁶.","kind":"performance","quote":"The parameters bθ is learned through training, satisfying LossP (bθ) ≤10−6. This implies that the MAE regularization term RP (θ)"},{"finding":"The measured loss of non‑negativity of the estimated density is about 10⁻⁷, negligible for practical purposes.","kind":"performance","quote":"the measure for loss of non-negativity | min(bg(·; bθ), 0)| is about 10−7, negligible for all practical purpos…"},{"finding":"European and Bermudan option prices computed using FourNet‑estimated transition densities exhibit impressive accuracy.","kind":"pricing-calibration","quote":"computed using estimated transition densities obtained through FourNet exhibit impressive accuracy."}],"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":1,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"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":"2026-11-14T18:22:32Z"},"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/"}