{"paper_id":"2512.16411","title":"Asymptotic and finite-sample distributions of one- and two-sample empirical relative entropy, with application to change-point detection","authors":["Matthieu Garcin","Louis Perot"],"paper_date":"2025-12-18","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2512.16411v1","page_url":"https://thequant.space/flowcharts/asymptotic-and-finite-sample-distributions-of-one--and-two-s/","scores":{"empirical_rigor":6,"math_complexity":8.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes an offline change‑point detection test based on the empirical relative entropy between two sub‑samples.","quote":"The method we put forward here is based on the empirical relative entropy DKL (bpn∥bqn), with the two distributions bpn and bqn estimated on the two sub‑samples.","summary":"Relative entropy, as a divergence metric between two distributions, can be used for offline change-point detection and extends classical methods that mainly rely on moment-based discrepancies. To build a statistical test suitable for this context, we study the distribution of empirical relative…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Under the null hypothesis the whole sequence is i.i.d.; under the alternative each half follows a different discrete distribution.","type":"statistical","stated":"explicit","quote":"Under the null hypothesis, X1, ..., X2n are identically distributed. Under the alternative hypothesis, there exists t⋆∈J2, 2n −1K such that X1, ..., Xt⋆are identically distributed and follow a discrete probability q, whereas Xt⋆+1, ..., X2n are also identically distributed but follow another discrete probability p."},{"assumption":"The test is applied in an offline setting with the change‑point at the centre (t⋆ = n).","type":"statistical","stated":"explicit","quote":"In the offline case, one generally focuses on t⋆= n [47], so that people consider a divergence statistic between the probabilities of the two sub‑samples."},{"assumption":"The two sub‑samples have equal size n.","type":"data","stated":"explicit","quote":"Our test thus consists in X1, ..., Xn ∼q and Xn+1, ..., X2n ∼p, with H0 corresponding to p = q and H1 to p̸ = q."},{"assumption":"The number of categories k is limited to k ≤ 8 in the two‑sample case to avoid empty categories.","type":"model","stated":"explicit","quote":"In the two‑sample case, we also constrain k to be less than or equal to 8; otherwise, simulations sometimes lead to empty categories, and consequently to zero estimated probabilities bqn, when n = 100."},{"assumption":"Agrawal’s condition x > (k−1)/n is always satisfied in the reported results.","type":"statistical","stated":"explicit","quote":"Agrawal’s condition x > (k−1)/n is always verified in our results and we have to discard the case k = 2 for Mardia’s bound."},{"assumption":"The analysis focuses on relatively small sample sizes (n < 50) where concentration inequalities are tighter than Berry‑Esseen bounds.","type":"other","stated":"implied","quote":"In addition, as we will see in Section 4.1, concentration inequalities give tighter bounds than the Berry‑Esseen approach when n is small."}]},"datasets":{"status":"available","items":[{"name":"Embrun temperature series","provider":"Météo‑France","kind":"macro","access":"public","period":"1999‑2024","universe":null,"quote":"We use a public dataset of temperatures at Embrun (Hautes‑Alpes, France), between January 1999 and December 2024, obtained from the website of"},{"name":"Realized volatility series of major stock indices","provider":"Oxford‑Man Institute of Quantitative Finance Realized Librar","kind":"other","access":"public","period":"2000‑2021","universe":"AEX, CAC 40, Nikkei 225, Oslo Exchange All‑share, S&P 500, VIX","quote":"time series of realized volatility computed with a five‑minute discretization of prices of stock indices, imported from the formerly available Oxford‑Man Institute of Quantitative Finance Realized Library"}],"known":[{"id":"bloomberg","name":"Bloomberg","provider":"Bloomberg L.P.","kind":"market-prices","access":"commercial","quote":"We import as well from Bloomberg the VIX, which is obtained from option prices on the SPX, in the same time period 2000-2021.","mentions":1,"used_in":1}],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"daily"},"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":"unclear","findings":[{"finding":"The relative‑entropy based test maintains the nominal confidence level while moments‑based tests (t‑test, F‑test) lose power in some scenarios.","kind":"statistical","quote":"The t‑test is now unable to detect change‑points when they exist. The ∆AIC method is liberal again, whereas all the other methods have an appropriate actual confidence level."},{"finding":"Concentration inequalities provide tighter finite‑sample bounds than Berry‑Esseen bounds for small n.","kind":"theoretical","quote":"In addition, as we will see in Section 4.1, concentration inequalities give tighter bounds than the Berry‑Esseen approach when n is small."},{"finding":"The asymptotic quantile slightly underestimates the true quantile for n < 50, with larger underestimation in the tail.","kind":"statistical","quote":"We observe that the quantile of the asymptotic distribution is very accurate: it only slightly underestimates the true quantile when n is small (less than 50) and this underestimation becomes more pronounced the further we move into the tail of the distribution."},{"finding":"Sanov’s bounds largely overestimate the quantile, while Agrawal’s bounds are close to the true quantile in both one‑ and two‑sample cases.","kind":"theoretical","quote":"Sanov’s bounds largely overestimate the quantile. Mardia’s bound is only slightly better than the best Sanov’s bound, whereas the two Agrawal’s bounds, which are very close to each other both in the one‑ and the two‑sample cases…"},{"finding":"Applications to climate and finance data show the method reveals climate change and changes in volatility dependence linked to macro‑economic events.","kind":"performance","quote":"Two applications to real data, namely climate and finance datasets, emphasize the practical relevance of this method. It makes the climate change visible and unveils modifications in the serial dependence of volatility that we can relate to macroeconomic events."}],"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":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":"2026-11-14T17:18:52Z"},"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/"}