{"paper_id":"2609.34474","title":"Deep kernel hedging","authors":["Jean-Loup Dupret","Donatien Hainaut","Edouard Motte"],"paper_date":"2026-09-28","paper_type":"theoretical","paper_url":"https://arxiv.org/pdf/2609.34474","page_url":"https://thequant.space/flowcharts/deep-kernel-hedging/","scores":{"empirical_rigor":7,"math_complexity":8.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a deep kernel hedging framework that combines deep learning with kernel methods, using a neural network embedding of input features and a random Fourier feature approximation.","quote":"We introduce a deep kernel hedging framework that combines the flexibility of deep learning with the structural inductive bias of kernel methods.","summary":"We introduce a deep kernel hedging framework that combines the flexibility of deep learning with the structural inductive bias of kernel methods. The hedging functional is restricted to a reproducing kernel Hilbert space whose kernel is parameterized through a neural network embedding of the input…","strategy":"deep kernel hedging"},"assumptions":{"status":"available","items":[{"assumption":"The kernel parameter space Θ is compact and the kernel Kθ(x,x′) is continuous in θ for all x,x′.","type":"statistical","stated":"explicit","quote":"Assumption 1. The following conditions hold: Θ ⊂Rm is compact, (H1) θ 7→Kθ(x, x′) is continuous on Θ, ∀x, x′ ∈X. (H2)"},{"assumption":"The hedging functional is restricted to a reproducing kernel Hilbert space (RKHS) associated with the deep kernel.","type":"model","stated":"explicit","quote":"The hedging functional is restricted to a reproducing kernel Hilbert space whose kernel is parameterized through a neural network embedding of the input features."}]},"datasets":{"status":"available","items":[{"name":"Synthetic dataset","provider":null,"kind":"synthetic","access":"unknown","period":null,"universe":null,"quote":"We evaluate the performance of the proposed deep kernel approach on both synthetic and real data and compare it with standard kernel methods and classical deep hedging architectures."},{"name":"S&P500 time series","provider":"S&P500 historical data","kind":"market-prices","access":"public","period":"2010-01-01 to 2026-05-31","universe":"S&P500 constituents","quote":"We construct our dataset using S&P500 historical data over the period from January 1st, 2010 to May 31st, 2026."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":"options","frequency":null},"data_resolution":"unclear"},"transaction_costs":{"status":"available","modeled":"no","headline_net_of_costs":false,"detail":null,"quote":null,"source":"front_matter","rule":"R1","candidates":{"front_matter":"no","evidence_card":"no","evidence_card_quoted":false},"meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"pricing-calibration","findings":[{"finding":"Deep kernel hedging achieves the lowest out-of-sample MSE across all maturities and training sample sizes, especially in low-data regimes.","kind":"performance","quote":"Overall, deep kernel hedging achieves the lowest MSE across all considered maturities and training sample sizes, and this improvement can also be seen in the other out-of-sample metrics (MAE, qupper0.95 , CVaRupper0.95 ) reported in Table 3."}],"reported_performance":{"strategy":"deep kernel hedging","sharpe":null,"sharpe_benchmark":null,"annual_return_pct":null,"total_return_pct":null,"max_drawdown_pct":null},"out_of_sample":{"method":"holdout","headline_out_of_sample":true}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":8,"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":"2026-11-14T17:04:06Z"},"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/"}