{"paper_id":"2407.20352","title":"Designing Time-Series Models With Hypernetworks & Adversarial Portfolios","authors":["Filip Staněk"],"paper_date":"2024-07-29","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2407.20352v1","page_url":"https://thequant.space/flowcharts/designing-time-series-models-with-hypernetworks--adversaria/","scores":{"empirical_rigor":8,"math_complexity":7,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a novel meta‑learning model that uses hypernetworks to create a parametric model tailored to a specific family of forecasting tasks.","quote":"we tested a novel meta-learning model that utilizes hypernetworks to design a parametric model tailored to a specific family of forecasting tasks.","summary":"This article describes the methods that achieved 4th and 6th place in the forecasting and investment challenges, respectively, of the M6 competition, ultimately securing the 1st place in the overall duathlon ranking. In the forecasting challenge, we tested a novel meta-learning model that utilizes…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The estimation function outputs the global minimizer of the in‑sample loss.","type":"model","stated":"explicit","quote":"A1: The estimation function κωp¨q outputs the global minimizer of the in-sample loss:"},{"assumption":"Training is conducted using a train‑train split rather than a train‑val split.","type":"model","stated":"explicit","quote":"A2: The training is conducted using a train-train split:"}]},"datasets":{"status":"available","items":[{"name":"M4 competition datasets","provider":null,"kind":"benchmark","access":"public","period":null,"universe":null,"quote":"Table B.2 displays the average MASE for OLS localized via MtMs with dθ = 2 on the M4 datasets."},{"name":"Sinusoidal regression simulation","provider":null,"kind":"synthetic","access":"public","period":null,"universe":null,"quote":"To evaluate the potential of the MtMs to find the most appropriate parametric model for a given family of prediction problems, we consider a simulation exercise originally proposed by Finn et al. (2017)"}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"unclear"},"transaction_costs":{"status":"available","modeled":"unclear","headline_net_of_costs":null,"detail":null,"quote":null,"source":"conflict","rule":"R4b","candidates":{"front_matter":"no","evidence_card":"n/a","evidence_card_quoted":false},"conflict_kind":"applicability","meaning":"the platform classifier and the paper-text extraction disagree, so no value is asserted"},"results":{"status":"available","evaluation_type":"unclear","findings":[{"finding":"The proposed method achieved 4th place in the forecasting challenge, 6th place in the investment challenge, and secured 1st place overall in the M6 duathlon ranking.","kind":"performance","quote":"This article describes the methods that achieved 4th and 6th place in the forecasting and investment challenges, respectively, of the M6 competition, ultimately securing the 1st place in the overall duathlon ranking."},{"finding":"The MtMs model outperforms state‑of‑the‑art meta‑learning approaches on the sinusoidal regression problem and performs excellently on the M4 competition.","kind":"predictive-accuracy","quote":"the fact that the MtMs model also outperforms state-of-the-art meta-learning approaches on the sinusoidal regression problem (Appendix A) and that it performs excellently on M4 (Appendix B) certainly shows great promise."},{"finding":"Simulations suggest that achieving the 6th rank in the investment challenge would likely not be repeated in a re‑run of the competition.","kind":"negative","quote":"our own simulations suggest that achieving the 6th rank would likely not be repeated if the competition were held again."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":13,"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":true,"code_url":"https://github.com/stanek-fi/M6","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":"2026-11-14T18:05:09Z"},"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/"}