{"paper_id":"2510.19130","title":"Denoising Complex Covariance Matrices with Hybrid ResNet and Random Matrix Theory: Cryptocurrency Portfolio Applications","authors":["Andres Garcia-Medina"],"paper_date":"2025-10-21","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2510.19130v2","page_url":"https://thequant.space/flowcharts/denoising-complex-covariance-matrices-with-hybrid-resnet-and/","scores":{"empirical_rigor":6,"math_complexity":8.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a hybrid covariance estimator that combines Random Matrix Theory regularization of eigenvalues with a deep Residual Neural Network that learns corrections to eigenvectors.","quote":"we introduce a power-law covariance model to characterize collective market dynamics and propose a hybrid estimator that integrates Random Matrix Theory (RMT) with deep Residual Neural Networks (ResNets). The RMT component regularizes the eigenvalue spectrum in high-dimensional noisy settings, while the ResNet learns d","summary":"Covariance matrices estimated from short, noisy, and non-Gaussian financial time series are notoriously unstable. Empirical evidence suggests that such covariance structures often exhibit power-law scaling, reflecting complex, hierarchical interactions among assets. Motivated by this observation…","strategy":"Ξ2S(CNN) two-step CNN-based estimator"},"assumptions":{"status":"available","items":[{"assumption":"The training period ends at the Bitcoin peak on 2021-11-09 and the out‑of‑sample test period covers the subsequent bear market.","type":"market","stated":"explicit","quote":"We split our dataset into training and testing periods. The splitting point is set to 2021-11-09, corresponding to the maximum closing value of Bitcoin (BTC) during the pandemic turmoil."},{"assumption":"Stablecoins are excluded because they do not reflect intrinsic cryptocurrency dynamics.","type":"data","stated":"explicit","quote":"Finally, we exclude all stablecoins (a total of 21), such as USDT or EURS, as their values are designed to remain pegged to fiat currencies or commodities (e.g., gold) and thus do not reflect the intrinsic dynamics of cryptocurrency markets."},{"assumption":"Portfolio allocations are computed using the MVP+ investment strategy on the estimated covariance matrices.","type":"execution","stated":"explicit","quote":"we obtain the optimal portfolio allocations w by applying the MVP+ investment strategy, using as input each of the covariance estimators presented in Section 3"},{"assumption":"The ResNet models are retrained at each rebalancing point with a rolling window of approximately one additional preceding year.","type":"execution","stated":"explicit","quote":"... the model is retrained at each rebalancing point using an extended training dataset that includes the in-sample period plus approximately one additional preceding year (282 days)."},{"assumption":"Turnover is used as a proxy for transaction costs, but no explicit cost model is incorporated into performance metrics.","type":"other","stated":"implied","quote":"Turnover measures the absolute difference between the asset weights at consecutive periods, normalized by the number of periods. A high value is associated with high transaction fees."}]},"datasets":{"status":"available","items":[{"name":"Daily returns of 89 major (non‑stable) cryptocurrencies","provider":"yfinance API","kind":"market-prices","access":"public","period":"2020-08-02 to 2025-07-31","universe":"Top 89 cryptocurrencies by market capitalization after filtering","quote":"We analyze the daily returns of the p = 89 major (non‑stable) cryptocurrencies by market capitalization over a five‑year period, from 2020-08-02 to 2025-07-31, yielding a total of n = 1825 observations. The data are retrieved using the yfinance API.","known_id":"yahoo-finance"}],"known":[{"id":"yahoo-finance","name":"Yahoo Finance","provider":"Yahoo","kind":"market-prices","access":"public","quote":"The data are retrieved using the yfinance API.","mentions":1,"used_in":1}],"sample":{"start":"2021-11","end":"2025-05","market":"cryptocurrency market","asset_class":"crypto","frequency":"daily"},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"no","headline_net_of_costs":false,"detail":null,"quote":"Turnover measures the absolute difference between the asset weights at consecutive periods, normalized by the number of periods. A high value is associated with high transaction fees.","source":"front_matter","rule":"R3","candidates":{"front_matter":"no","evidence_card":"no","evidence_card_quoted":true},"card_detail":null,"card_quote":"Turnover measures the absolute difference between the asset weights at consecutive periods, normalized by the number of periods. A high value is associated with high transaction fees.","meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"The two‑step CNN‑based estimator (Ξ2S(CNN)) achieves the highest cumulative portfolio return (17.14%) and the best Sharpe ratio among all estimators in the walk‑forward MVP+ analysis.","kind":"performance","quote":"Ξ2S(CNN) 1.74 17.14% 46.60% 0.37 -63.63% 1.34"},{"finding":"The hybrid two‑step estimator (Ξ2S(H)) attains the minimum MV loss for the block‑diagonal covariance model, while the single‑step ΞCNN minimizes Frobenius loss for that model.","kind":"theoretical","quote":"We found that the two‑step estimator based on the ResNet architecture (Ξ2S(CNN)) minimizes the Frobenius loss function for the block‑diagonal model. For the same model, the two‑step hybrid estimator (Ξ2S(H)) attains the minimum value of the MV loss function."},{"finding":"When the covariance follows a power‑law structure, none of the state‑of‑the‑art estimators outperform the naive estimator in Frobenius loss, but the two‑step hybrid estimator yields the lowest MV loss.","kind":"theoretical","quote":"in this case, none of the state‑of‑the‑art estimators outperform the naive one in terms of the Frobenius loss. However, regarding the MV loss, the two‑step hybrid estimator achieves the lowest noise level."},{"finding":"Empirical cryptocurrency data exhibit an eigenvalue spectrum with an approximate power‑law decay (α = 0.2), matching the stylized facts of both nested hierarchical and power‑law covariance models.","kind":"statistical","quote":"the eigenvalue spectrum displays an approximate power‑law decay with coefficient α = 0.2."},{"finding":"Across all models, MV loss systematically decreases when using ResNet‑based estimators, indicating better risk control for portfolio optimization.","kind":"statistical","quote":"a consistent pattern emerges MV loss systematically decreases across all models when using the ResNet‑based estimators."}],"reported_performance":{"strategy":"Ξ2S(CNN) two-step CNN-based estimator","sharpe":1.34,"sharpe_benchmark":-0.5,"annual_return_pct":17.14,"total_return_pct":174,"max_drawdown_pct":63.63},"out_of_sample":{"method":"walk-forward","headline_out_of_sample":true}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":36,"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":"2026-11-14T17:24:01Z"},"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/"}