{"paper_id":"2405.13513","title":"An Asymptotic CVaR Measure of Risk for Markov Chains","authors":["Shivam Patel","Vivek Borkar"],"paper_date":"2024-05-22","paper_type":"theoretical","paper_url":"https://arxiv.org/pdf/2405.13513v1","page_url":"https://thequant.space/flowcharts/an-asymptotic-cvar-measure-of-risk-for-markov-chains/","scores":{"empirical_rigor":6.5,"math_complexity":8.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes an asymptotic variant of CVaR (ACVaR) and a stochastic approximation algorithm to compute it for Markov chains.","quote":"We present a complete simulation based approach for sequentially computing Asymptotic CVaR (ACVaR), a risk measure we define on limiting empirical averages of markovian rewards. We adapt the results therein to the problem of evaluating Asymptotic CVaR (ACVaR), a concept defined here, and provide theoretical justification for it as well as supporting numerical experiments for the proposed computational scheme.","summary":"Risk sensitive decision making finds important applications in current day use cases. Existing risk measures consider a single or finite collection of random variables, which do not account for the asymptotic behaviour of underlying systems. Conditional Value at Risk (CVaR) is the most commonly…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The underlying process is a finite‑state Markov chain with a reward function g defined on the states.","type":"model","stated":"explicit","quote":"Let V ∗:= Vζ∗, ρ∗:= ρζ∗. Theorem 2.2.","support":"full"},{"assumption":"Large‑deviation theory applies to the empirical averages of the rewards.","type":"statistical","stated":"explicit","quote":"The proof uses an extension to Markov processes of the Bahadur-Rao theorem for exact asymptotics in large deviations from [10].","support":"full"},{"assumption":"The limiting cumulative distribution function of the reward is piecewise constant and can be approximated by a continuous interpolation.","type":"statistical","stated":"explicit","quote":"Let F(·) denote the limiting cumulative distribution function (CDF) of the reward g(Xn). Nevertheless, it is convenient to seek a suitable continuous and continuously increasing interpolation so that its inverse is likewise, in order to avoid some numerical issues.","support":"full"},{"assumption":"A Gaussian kernel density estimator provides a suitable estimate of the inverse CDF needed for the threshold.","type":"statistical","stated":"explicit","quote":"In the present work, we have used a Gaussian kernel density estimate [5]. Gaussian kernel estimation was our method of choice justified by its good empirical performance.","support":"full"},{"assumption":"Two‑time‑scale stochastic approximation with step sizes a(n)=k/(1+(n+1)^0.6) and b(n)=k/(1+(n+1)^0.8) ensures convergence of the adaptive scheme.","type":"model","stated":"explicit","quote":"The simulation steps are performed with varying step-sizes which are in agreement with the two time-scale stochastic approximation formalism mentioned earlier. Step sizes are controlled by a single scaling parameter k as a(n) = k 1 + (n + 1)0.6 , b(n) = k 1 + (n + 1)0.8 .","support":"full"},{"assumption":"If a state is never visited, its reward is set to zero.","type":"other","stated":"explicit","quote":"If any state is unexplored, we nominally assign it a zero reward.","support":"full"}]},"datasets":{"status":"available","items":[{"name":"Synthetic Markov chain simulations (40, 75, 150 state chains)","provider":null,"kind":"synthetic","access":"unknown","period":null,"universe":"finite state spaces of sizes 40, 75, 150","quote":"For the sake of brevity, we present here a comparison of 70th, 85th, 90th percentile thresholding in a 40 State Markov chain along with the 90th percentile thresholding in 75 and 150 state Markov chains.","support":"full"},{"name":"Deterministic rewards drawn from Uniform(0,4)","provider":null,"kind":"synthetic","access":"unknown","period":null,"universe":null,"quote":"We also tested our method on deterministic rewards that are chosen from a Unif(0, 4) distribution initially, obtaining similar convergence results.","support":"full"}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"synthetic"},"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":"none","findings":[{"finding":"The adaptive stochastic approximation scheme converges in under 80 000 steps for all tested state spaces and thresholds.","kind":"theoretical","quote":"We observe convergence for all the cases in under 80K steps, with (possibly) varying step size parameter k required for different state spaces and different values of c.","support":"full"},{"finding":"Numerical experiments show that ACVaR estimates align with the theoretical expectations across 70th, 85th, and 90th percentile thresholds.","kind":"performance","quote":"For the sake of brevity, we present here a comparison of 70th, 85th, 90th percentile thresholding in a 40 State Markov chain along with the 90th percentile thresholding in 75 and 150 state Markov chains.","support":"full"},{"finding":"When the reward process is constant, ACVaR reduces to the classical CVaR, confirming consistency with the standard risk measure.","kind":"theoretical","quote":"For Xn ≡a fixed random variable, this would reduce ACVaR to CVaR as desired.","support":"full"},{"finding":"The algorithm enjoys theoretical guarantees derived from large‑deviation theory and two‑time‑scale stochastic approximation.","kind":"theoretical","quote":"Our algorithm enjoys theoretical guarantees, and we numerically evaluate its performance over a variety of test cases.","support":"full"}],"reported_performance":null,"out_of_sample":{"method":"none","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":26,"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":2,"extracted_at":"2026-11-14T19:57:29Z"},"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/"}