{"paper_id":"2511.01125","title":"One model to solve them all: 2BSDE families via neural operators","authors":["Takashi Furuya","Anastasis Kratsios","Dylan Possamaï","Bogdan Raonić"],"paper_date":"2025-11-03","paper_type":"theoretical","paper_url":"https://arxiv.org/pdf/2511.01125v1","page_url":"https://thequant.space/flowcharts/one-model-to-solve-them-all-2bsde-families-via-neural-opera/","scores":{"empirical_rigor":1.5,"math_complexity":9.2,"quadrant":"Lab Rats"},"proposes":{"status":"available","statement":"The paper proposes a generative neural operator model based on Kolmogorov–Arnold networks to approximate the solution operator for infinite families of second‑order backward stochastic differential equations (2BSDEs).","quote":"We introduce a mild generative variant of the classical neural operator model, which leverages Kolmogorov--Arnold networks to solve infinite families of second-order backward stochastic differential equations ($2$BSDEs) on regular bounded Euclidean domains with random terminal time.","summary":"We introduce a mild generative variant of the classical neural operator model, which leverages Kolmogorov–Arnold networks to solve infinite families of second-order backward stochastic differential equations (2BSDEs) on regular bounded Euclidean domains with random terminal time. Our first main…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The coefficient maps γ, µ and λ are infinitely differentiable on the closure of the domain, uniformly elliptic and bounded, with λ ≥ 0 and λ ≥ ∇·µ.","type":"model","stated":"explicit","quote":"The maps γ : D −→Rd×d, µ : D −→Rd, and λ : D −→R satisfy the following conditions (i) γ ∈C∞( ¯D; Rd×d), µ ∈C∞( ¯D; Rd), and λ ∈C∞( ¯D; R) where C∞( ¯D; Rd) and C∞( ¯D; Rd×d) denote the spaces of all d-dimensional vector-valued and d × d matrix-valued functions that are infinitely differentiable on D and whose derivatives admit continuous extensions to the closure ¯D; (ii) γ is uniformly elliptic and bounded in the","support":"full"},{"assumption":"The auxiliary function ˜f is analytic near zero, represented by a finite power series with no constant or linear terms, and its higher‑order coefficients are smooth.","type":"model","stated":"explicit","quote":"Next, we summaries our main assumptions on ˜f. Assumption 3.9. The map ˜f : D × R −→R satisfies 11 (i) there exists δ0 > 0 and H ∈N⋆\\ {1, 2} such that ˜f(x, z) = H X h=0 ∂h z ˜f(x, 0) h! zh, for ∥z∥< δ0, and x ∈D; (ii) ˜f(·, 0) = ∂1 z ˜f(·, 0) = 0; (iii) ∂h z ˜f(·, 0) ∈C∞( ¯D; R) for all h ∈{2, . . . , H}.","support":"full"},{"assumption":"A smallness condition holds: there exists δ < δ₀ such that C₁δ < 1, C₂δ < 1, C₃δ < 1, where the constants depend only on problem parameters.","type":"model","stated":"explicit","quote":"Finally, we formulate a smallness assumption. Assumption 3.10. We take 0 < δ < δ0 (where δ0 comes from Assumption 3.9.(i)) so that C1δ < 1, ρ := C2δ < 1, C3δ < 1, where the positive constants C1, C2, C3 will appear in (A.6), (A.7), and (A.13), and depend only p, d, D, ˜f, γ, and µ.","support":"full"},{"assumption":"The domain D is a bounded open set with a Lipschitz boundary in ℝᵈ.","type":"model","stated":"explicit","quote":"Suppose that D is a bounded open set with Lipschitz boundary in Rd.","support":"full"}]},"datasets":{"status":"none_found","items":[],"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":"unclear","findings":[{"finding":"The solution operator for a broad class of 2BSDE families is approximable by the proposed neural operator model.","kind":"theoretical","quote":"Our first main result shows that the solution operator associated with a broad range of $2$BSDE families is approximable by appropriate neural operator models. We then identify a structured subclass of (infinite) families of $2$BSDEs whose neural operator approximation requires only a polynomial number of parameters in the reciprocal approximation rate, as opposed to the exponential requirement in general worst-case","support":"full"},{"finding":"For a structured subclass of 2BSDE families, the neural operator achieves exponential approximation rates with only a polynomial number of parameters in the reciprocal error tolerance.","kind":"theoretical","quote":"We then identify a structured subclass of (infinite) families of $2$BSDEs whose neural operator approximation requires only a polynomial number of parameters in the reciprocal approximation rate, as opposed to the exponential requirement in general worst-case neural operator guarantees. Under the above assumptions, we have the following approximation guarantee for the solution operator of the PDE associated with our","support":"full"}],"reported_performance":null,"out_of_sample":{"method":"none","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":7,"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":2,"extracted_at":"2026-11-14T19:46:30Z"},"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/"}