{"paper_id":"2405.02570","title":"Gradient-enhanced sparse Hermite polynomial expansions for pricing and hedging high-dimensional American options","authors":["Jiefei Yang","Guanglian Li"],"paper_date":"2024-05-04","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2405.02570v2","page_url":"https://thequant.space/flowcharts/gradient-enhanced-sparse-hermite-polynomial-expansions-for-p/","scores":{"empirical_rigor":7,"math_complexity":8.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a gradient-enhanced least squares Monte Carlo (G-LSM) method that uses sparse Hermite polynomial expansions to price and hedge high‑dimensional American options.","quote":"We propose an efficient and easy-to-implement gradient-enhanced least squares Monte Carlo method for computing price and Greeks (i.e., derivatives of the price function) of high-dimensional American options.","summary":"We propose an efficient and easy-to-implement gradient-enhanced least squares Monte Carlo method for computing price and Greeks (i.e., derivatives of the price function) of high-dimensional American options. It employs the sparse Hermite polynomial expansion as a surrogate model for the…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The discounted payoff function g_k(·) is L‑Lipschitz continuous.","type":"model","stated":"explicit","quote":"Assumption 5.1. The discounted payoﬀfunction gk(·) is L-Lipschitz continuous: for k = 0, 1, . . . , N (5.1) |gk(s) −gk(s′)| ≤L∥s −s′∥, ∀s, s′ ∈Rd."},{"assumption":"Underlying assets follow the multi‑asset Black‑Scholes model with correlated geometric Brownian motions.","type":"market","stated":"explicit","quote":"One of the most classical models for high-dimensional American option pricing is the multi-asset Black‑Scholes model. Under the risk‑neutral probability Q, the prices of d underlying assets, St = S1t , . . . , Sdt ⊤, follow the correlated geometric Brownian motions (2.4) dSi t = (r −δi)Si t dt + σiSi t d ˜W i t with Si"},{"assumption":"The continuation value function can be reformulated as a function of independent Brownian motions after a linear transformation.","type":"model","stated":"explicit","quote":"Since the corresponding CVF can be reformulated as a function of independent Brownian motions and the associated best approximation error in the sparse Hermite polynomial ansatz space PI,k can be rigorously established, cf. Lemma 5.2."}]},"datasets":{"status":"available","items":[{"name":"Bermudan geometric basket put (benchmark)","provider":null,"kind":"benchmark","access":"unknown","period":null,"universe":null,"quote":"Geometric basket options are benchmark tests for high-dimensional option pricing problems, since they can be reduced to one-dimensional problems, and thus highly accurate prices are available."},{"name":"Max‑call with d symmetric assets","provider":null,"kind":"synthetic","access":"unknown","period":null,"universe":null,"quote":"Max-call with d symmetric assets K = 100, T = 3, r = 0.05, δi = 0.1, σi = 0.2, ρij = 0, N = 9"},{"name":"Max‑call with d asymmetric assets","provider":null,"kind":"synthetic","access":"unknown","period":null,"universe":null,"quote":"Max-call with d asymmetric assets σi = ( 0.08 + 0.32 × (i −1)/(d −1), if d ≤5 0.1 + i/(2d), if d > 5"},{"name":"Put option under Heston model","provider":null,"kind":"synthetic","access":"unknown","period":null,"universe":null,"quote":"Put option under Heston model K = 10, T = 0.25, r = 0.1, v0 = 0.0625, ρ = 0.1, κ = 5, θ = 0.16, ν = 0.9, N = 50"}],"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":"G‑LSM achieves substantially lower relative pricing errors than standard LSM in high dimensions (e.g., 0.55% vs 5.15% for d=15).","kind":"performance","quote":"G-LSM has a relative error 0.55% for d = 15, which is almost ten times smaller than that by LSM."},{"finding":"G‑LSM matches the accuracy of recent deep‑neural‑network methods up to dimension 100 while keeping computational cost nearly identical to LSM.","kind":"performance","quote":"It outperforms the state-of-the-art least squares Monte Carlo method with more accurate price, Greeks, and optimal exercise strategies in high dimensions but with nearly identical computational cost, and it can deliver comparable results with recent neural network-based methods up to dimension 100."},{"finding":"The method retains low complexity for gradient evaluation and ease of implementation, making it suitable for high‑dimensional problems.","kind":"theoretical","quote":"The method enjoys low complexity for the gradient evaluation, ease of implementation and high accuracy for high-dimensional problems."}],"reported_performance":null,"out_of_sample":{"method":"none","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":39,"citations":{"cited_by_in_corpus":1,"by_independent_authors":1,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":1,"unclassified":0},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":true,"code_url":"https://github.com/jiefeiy/glsm-american","note":null},"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":"2026-11-14T18:10:03Z"},"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/"}