{"paper_id":"2410.14788","title":"Simultaneously Solving FBSDEs and their Associated Semilinear Elliptic PDEs with Small Neural Operators","authors":["Takashi Furuya","Anastasis Kratsios"],"paper_date":"2024-10-18","paper_type":"theoretical","paper_url":"https://arxiv.org/pdf/2410.14788v2","page_url":"https://thequant.space/flowcharts/simultaneously-solving-fbsdes-and-their-associated-semilinea/","scores":{"empirical_rigor":2,"math_complexity":8.5,"quadrant":"Lab Rats"},"proposes":{"status":"available","statement":"The paper proposes a tailored neural operator architecture that, by factoring out the singular part of the Green's function and incorporating the Doléans–Dade exponential of a common non‑Markovian factor, can approximate the solution operator of a structured family of non‑Markovian BSDEs with a numb","quote":"We exhibit the first polynomial-scaling regime for NO approximations of solution operators in stochastic analysis; by identifying structured families of \\emph{non-Markovian} BSDEs with randomized terminal condition parameterized by the Sobolev-regular terminal condition and by Sobolev-regular additive nonlinear perturbations of the generator. We prove that their solution operator can be approximated (uniformly over","summary":"Forward-backwards stochastic differential equations (FBSDEs) play an important role in optimal control, game theory, economics, mathematical finance, and in reinforcement learning. Unfortunately, the available FBSDE solvers operate on \\textit{“individual”} FBSDEs, meaning that they cannot provide a…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"A filtered probability space satisfying the usual conditions and supporting a d‑dimensional Brownian motion is fixed.","type":"model","stated":"explicit","quote":"To explain, we fix a filtered probability space (Ω, F, F def. = (Ft)t≥0, P) satisfying the usual conditions and supporting a d(≥2)-dimensional Brownian motion W· def. = (Wt)t≥0.","support":"full"},{"assumption":"The non‑Markovian factor β· satisfies a strong Novikov condition (Assumption 5).","type":"model","stated":"explicit","quote":"5.4.1 Examples of Non-Markovian Factors β· in Equation 2 Two simple examples of non-Markovian β· satisfying our Strong Novikov condition in Assumption 5 are the following: Example 6 (General Bounded Predictable Factor) Let β be d-dimensional predictable and assume ∥βt∥≤M for all t ∈[0, T] a.s. Then E","support":"full"}]},"datasets":{"status":"none_found","items":[],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"none"},"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":"none","findings":[{"finding":"The solution operator of the identified family of BSDEs can be uniformly approximated by the proposed neural operator with a number of parameters that grows polynomially in 1/ε, establishing a polynomial‑scaling regime.","kind":"theoretical","quote":"We prove that their solution operator can be approximated (uniformly over the family) by a tailored NO whose number of trainable parameters grows \\emph{polynomially} in $1/\\varepsilon$.","support":"full"},{"finding":"The convolutional variant of the neural operator can approximate the associated semilinear elliptic Dirichlet problem, and consequently the FBNO model approximates the BSDE solution operator with only logarithmic increases in component complexity for linear ga","kind":"theoretical","quote":"Proofs We will prove Theorem 1 in two steps First, we show that our convolutional variant (Definition 2) of the classical neural operator model can approximate the solution operator to the semiliinear elliptic Dirichlet problem associated to our family of FBSDEs relying on the connection between FBSDEs and semilinear Elliptic PDEs due in Pardoux (1998). This is the content of Theorem 2, which is our first main","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":5,"citations":{"cited_by_in_corpus":3,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":3},"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":"2026-11-14T19:54:22Z"},"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/"}