{"paper_id":"2504.13529","title":"Improving Bayesian Optimization for Portfolio Management with an Adaptive Scheduling","authors":["Zinuo You","John Cartlidge","Karen Elliott","Menghan Ge","Daniel Gold"],"paper_date":"2025-04-18","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2504.13529v3","page_url":"https://thequant.space/flowcharts/improving-bayesian-optimization-for-portfolio-management-wit/","scores":{"empirical_rigor":6,"math_complexity":7.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes TPE-AS, a novel Bayesian optimization framework that improves search stability and efficiency for black-box portfolio models under limited observation budgets.","quote":"a novel Bayesian optimization framework (TPE-AS) that improves search stability and efficiency for black-box portfolio models","summary":"Existing black-box portfolio management systems are prevalent in the financial industry due to commercial and safety constraints, though their performance can fluctuate dramatically with changing market regimes. Evaluating these non-transparent systems is computationally expensive, as fixed budgets…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The evaluation budget is fixed and limited, restricting the number of possible observations.","type":"execution","stated":"implied","quote":"fixed budgets limit the number of possible observations"},{"assumption":"Portfolio performance can fluctuate dramatically with changing market regimes.","type":"market","stated":"implied","quote":"performance can fluctuate dramatically with changing market regimes"}]},"datasets":{"status":"none_found","items":[],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"unclear"},"transaction_costs":{"status":"available","modeled":"no","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R1","candidates":{"front_matter":"no","evidence_card":"unclear","evidence_card_quoted":false},"meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"TPE-AS achieves the highest annualized Sharpe ratio in eight out of twelve test cases, outperforming both GP‑based and BNN‑based baselines.","kind":"performance","quote":"TPE-AS achieves the highest annualized Sharpe ratio in eight out of twelve test cases, outperforming both GP-based and BNN-based baselines"},{"finding":"TPE-AS consistently exhibits the lowest variance of Sharpe ratios across all twelve scenarios, with a maximum observed variance of 0.170 versus 1.083 for BNN‑UCB.","kind":"performance","quote":"Table 2 further highlights optimization stability via the variance of achieved Sharpe ratios. Here, TPE-AS consistently exhibits the lowest variance across all twelve scenarios, with its maximum observed variance just 0.170 (in M2-S2) versus BNN-UCB’s 1.083 under the same scenario"},{"finding":"Each optimization step of TPE‑AS takes 43.22–58.76 seconds, up to 1.77 seconds faster per step than GP‑UCB and 10%–30% faster than BNN‑based methods.","kind":"performance","quote":"TPE-AS completes each step in 43.22–58.76 s, outpacing the nearest competitor, GP-UCB, by up to 1.77 s per step and offering a 10%–30% speed-up over BNN‑based methods"}],"reported_performance":null,"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":20,"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/pixelhero98/TPE-AS","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":"2026-11-14T17:40:43Z"},"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/"}