pith. sign in

arxiv: 2311.15333 · v5 · submitted 2023-11-26 · 💱 q-fin.RM · math.PR· q-fin.CP

Asymptotic Error Analysis of Multilevel Stochastic Approximations for the Value-at-Risk and Expected Shortfall

St\'ephane Cr\'epey , Noufel Frikha , Azar Louzi , Gilles Pag\`es This is my paper

Pith reviewed 2026-05-24 06:26 UTC · model grok-4.3

classification 💱 q-fin.RM math.PRq-fin.CP
keywords value-at-riskexpected shortfallstochastic approximationmultilevel methodscentral limit theoremasymptotic analysisrisk management
0
0 comments X

The pith

Central limit theorems are established for the renormalized estimation errors of nested stochastic approximation algorithms and their multilevel accelerations when computing Value-at-Risk and Expected Shortfall.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper builds on a prior nested stochastic approximation algorithm and its multilevel version for estimating Value-at-Risk and Expected Shortfall of a random financial loss. It proves that suitably renormalized estimation errors for both algorithms, as well as their averaged versions, converge in distribution to normal limits. The proofs rely on verifying conditions that permit application of central limit theorems to these recursive stochastic schemes. A numerical example is provided to illustrate the findings. The results supply asymptotic justification for the reliability and error behavior of these computational procedures in risk quantification.

Core claim

We establish central limit theorems for the renormalized estimation errors associated with both the nested stochastic approximation algorithm and its multilevel acceleration, as well as their averaged versions, for computing the value-at-risk and expected shortfall of a random financial loss.

What carries the argument

Central limit theorems for renormalized estimation errors of nested stochastic approximation schemes and their multilevel accelerations.

If this is right

  • The estimation errors of the algorithms admit normal approximations for large iteration counts, enabling asymptotic confidence intervals.
  • Averaging the iterates preserves the central limit theorem property for both the standard and multilevel schemes.
  • The multilevel acceleration inherits the same asymptotic normality as the base algorithm under the stated conditions.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The CLTs open the possibility of comparing asymptotic variances between the multilevel and standard algorithms to quantify efficiency gains.
  • The framework could be tested on portfolio loss distributions with heavier tails to check robustness beyond the numerical example.

Load-bearing premise

The nested stochastic approximation algorithm and its multilevel acceleration satisfy the technical conditions on step-size sequences, moment bounds, and regularity of the loss distribution needed for the central limit theorems to apply.

What would settle it

Numerical simulation or theoretical counterexample in which the renormalized errors fail to converge to a normal distribution when the step-size and moment conditions are met.

Figures

Figures reproduced from arXiv: 2311.15333 by Azar Louzi, Gilles Pag\`es, Noufel Frikha, St\'ephane Cr\'epey.

Figure 1
Figure 1. Figure 1: Joint distributions of the renormalized VaR and ES estimation errors. 19 [PITH_FULL_IMAGE:figures/full_fig_p019_1.png] view at source ↗
read the original abstract

Cr\'epey, Frikha, and Louzi (2025) introduced a nested stochastic approximation algorithm and its multilevel acceleration to compute the value-at-risk and expected shortfall of a random financial loss. We hereby establish central limit theorems for the renormalized estimation errors associated with both algorithms as well as their averaged versions. Our findings are substantiated through a numerical example.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

0 major / 3 minor

Summary. The manuscript establishes central limit theorems for the renormalized estimation errors of the nested stochastic approximation algorithm and its multilevel acceleration (introduced in Crép ey et al. 2025) for computing Value-at-Risk and Expected Shortfall, as well as for the corresponding averaged versions. The CLTs are derived under explicitly stated technical conditions on step-size sequences, moment bounds, and loss distribution regularity, with proofs based on martingale arguments after linearization; results are illustrated by a numerical example.

Significance. The CLTs supply the first asymptotic normality results for these specific multilevel SA schemes, enabling rigorous error analysis and parameter tuning for VaR/ES estimation in finance. Explicit verification of the required conditions under the problem setup of the preceding paper, together with standard martingale-CLT techniques, strengthens the theoretical foundation without introducing new assumptions.

minor comments (3)
  1. [§1] §1 (Introduction): the sentence claiming the CLTs are 'new derivations' should explicitly note that the underlying algorithms and their convergence (without rates) originate in the 2025 reference, to prevent any misreading of the contribution.
  2. [Numerical example] Numerical example (final section): the plots and tables report point estimates but omit Monte-Carlo standard errors or confidence bands; adding these would make the visual agreement with the predicted asymptotic variances more convincing.
  3. [Theorems 3.1–3.4] Theorem statements: the precise form of the asymptotic variance (e.g., whether it involves the density at the quantile) is left implicit in the main text; a short remark or reference to the explicit expression derived in the proof would improve readability.

Simulated Author's Rebuttal

0 responses · 0 unresolved

We thank the referee for the positive assessment of our manuscript, the accurate summary of its contributions, and the recommendation of minor revision. No specific major comments appear in the report.

Circularity Check

0 steps flagged

Minor self-citation to prior algorithm introduction; CLT derivations remain independent

full rationale

The paper cites Crépey, Frikha, and Louzi (2025) solely for the definition and introduction of the nested stochastic approximation algorithm and its multilevel acceleration. The central claim consists of new central limit theorems derived via standard martingale CLT arguments after linearization, with all technical conditions (step-size sequences, moment bounds, regularity) stated explicitly in the theorem statements and verified under the problem setup. No load-bearing step in the derivation chain reduces by construction to the self-cited work, no fitted inputs are renamed as predictions, and no uniqueness theorem or ansatz is smuggled via overlapping-author citation. The numerical example serves only as illustration.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Only the abstract is available; no explicit free parameters, axioms, or invented entities are described.

pith-pipeline@v0.9.0 · 5604 in / 1167 out tokens · 21786 ms · 2026-05-24T06:26:51.124412+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

35 extracted references · 35 canonical work pages · 1 internal anchor

  1. [1]

    On the coherence of expected shortfall

    C. Acerbi and D. Tasche. “On the coherence of expected shortfall”. In:Journal of Banking & Finance26.7 (2002), pp. 1487–1503

    work page 2002

  2. [2]

    Computing VaR and CVaR using stochastic approx- imation and adaptive unconstrained importance sampling

    O. Bardou, N. Frikha, and G. Pagès. “Computing VaR and CVaR using stochastic approx- imation and adaptive unconstrained importance sampling”. In:Monte Carlo Methods and Applications 15.3 (2009), pp. 173–210

    work page 2009

  3. [3]

    CVaR hedging using quantization-based stochastic approximation algorithm

    O. Bardou, N. Frikha, and G. Pagès. “CVaR hedging using quantization-based stochastic approximation algorithm”. In:Mathematical Finance26.1 (2016), pp. 184–229. 54

    work page 2016

  4. [4]

    Recursive computation of value-at-risk and condi- tional value-at-risk using MC and QMC

    O. Bardou, N. Frikha, and G. Pagès. “Recursive computation of value-at-risk and condi- tional value-at-risk using MC and QMC”. In:Monte Carlo and Quasi-Monte Carlo Methods

    work page

  5. [5]

    Springer, 2009, pp. 193–208

    work page 2009

  6. [6]

    Stochastic ap- proximation schemes for economic capital and risk margin computations

    D. Barrera, S. Crépey, B. Diallo, G. Fort, E. Gobet, and U. Stazhynski. “Stochastic ap- proximation schemes for economic capital and risk margin computations”. In:ESAIM: Proceedings and Surveys65 (2019), pp. 182–218

    work page 2019

  7. [7]

    Basel Committee on Banking Supervision.Consultative document: Fundamental Review of the Trading Book: A revised market risk framework. 2013. url: bis.org/publ/bcbs265. pdf

    work page 2013

  8. [8]

    An old-new concept of convex risk measures: the optimized certainty equivalent

    A. Ben-Tal and M. Teboulle. “An old-new concept of convex risk measures: the optimized certainty equivalent”. In:Mathematical Finance17.3 (2007), pp. 449–476

    work page 2007

  9. [9]

    Stochastic approximation algorithms for superquantiles estimation

    B. Bercu, M. Costa, and S. Gadat. “Stochastic approximation algorithms for superquantiles estimation”. In:Electronic Journal of Probability26 (2021), pp. 1–29

    work page 2021

  10. [10]

    Non asymptotic controls on a recursive superquantile approxi- mation

    M. Costa and S. Gadat. “Non asymptotic controls on a recursive superquantile approxi- mation”. In:Electronic Journal of Statistics15.2 (2021), pp. 4718–4769

    work page 2021

  11. [11]

    Costa, S

    M. Costa, S. Gadat, and L. Huang. CV@R penalized portfolio optimization with biased stochastic mirror descent. 2024. arXiv:2402.11999 [math.OC]

    work page arXiv 2024

  12. [12]

    A Multilevel Stochastic Approximation Algorithm for Value-at-Risk and Expected Shortfall Estimation

    S. Crépey, N. Frikha, and A. Louzi. A multilevel stochastic approximation algorithm for value-at-risk and expected shortfall estimation. 2023. arXiv:2304.01207 [q-fin.CP]

    work page internal anchor Pith review Pith/arXiv arXiv 2023

  13. [13]

    General multilevel adaptations for stochastic approx- imation algorithms of Robbins–Monro and Polyak–Ruppert type

    S. Dereich and T. Müller-Gronbach. “General multilevel adaptations for stochastic approx- imation algorithms of Robbins–Monro and Polyak–Ruppert type”. In:Numerische Mathe- matik 142.2 (2019), pp. 279–328

    work page 2019

  14. [14]

    M. Duflo. Algorithmes Stochastiques. Springer Berlin, Heidelberg, 1996

    work page 1996

  15. [15]

    Combination of multivariate Gaussian distributions through error ellipses

    O. Erten and C. Deutsch. “Combination of multivariate Gaussian distributions through error ellipses.” In:Geostatistics Lessons(2020)

    work page 2020

  16. [16]

    Directive of the European Parliament and of the Council on the taking-up and pursuit of the business of insurance and reinsurance (Solvency II)

    European Parliament and the Council. Directive of the European Parliament and of the Council on the taking-up and pursuit of the business of insurance and reinsurance (Solvency II). 2009. url: eur-lex.europa.eu/eli/dir/2009/138/oj

    work page 2009

  17. [17]

    Convex risk measures

    H. Föllmer and A. Schied. “Convex risk measures”. In:Encyclopedia of Quantitative Fi- nance. John Wiley & Sons, Ltd, 2010

    work page 2010

  18. [18]

    Central limit theorems for stochastic approximation with controlled Markov chain dynamics

    G. Fort. “Central limit theorems for stochastic approximation with controlled Markov chain dynamics”. In:ESAIM: PS 19 (2015), pp. 60–80

    work page 2015

  19. [19]

    Multi-level stochastic approximation algorithms

    N. Frikha. “Multi-level stochastic approximation algorithms”. In:The Annals of Applied Probability 26.2 (2016), pp. 933–985

    work page 2016

  20. [20]

    Shortfall risk minimization in discrete time financial market models

    N. Frikha. “Shortfall risk minimization in discrete time financial market models”. In:SIAM Journal on Financial Mathematics5.1 (2014), pp. 384–414

    work page 2014

  21. [21]

    Optimal non-asymptotic analysis of the Ruppert–Polyak av- eraging stochastic algorithm

    S. Gadat and F. Panloup. “Optimal non-asymptotic analysis of the Ruppert–Polyak av- eraging stochastic algorithm”. In:Stochastic Processes and their Applications156 (2023), pp. 312–348

    work page 2023

  22. [22]

    Multilevel Monte Carlo path simulation

    M. B. Giles. “Multilevel Monte Carlo path simulation”. In:Operations Research56.3 (2008), pp. 607–617

    work page 2008

  23. [23]

    Multilevel nested simulation for efficient risk estimation

    M. B. Giles and A.-L. Haji-Ali. “Multilevel nested simulation for efficient risk estimation”. In: SIAM/ASA Journal on Uncertainty Quantification7.2 (2019), pp. 497–525

    work page 2019

  24. [24]

    M. B. Giles, A.-L. Haji-Ali, and J. Spence.Efficient risk estimation for the credit valuation adjustment. 2023. arXiv:2301.05886 [q-fin.CP]. 55

    work page arXiv 2023

  25. [25]

    Weak error for nested multilevel Monte Carlo

    D. Giorgi, V. Lemaire, and G. Pagès. “Weak error for nested multilevel Monte Carlo”. In: Methodology and Computing in Applied Probability22 (3 2020), pp. 1325–1348

    work page 2020

  26. [26]

    Nested simulation in portfolio risk measurement

    M. B. Gordy and S. Juneja. “Nested simulation in portfolio risk measurement”. In:Man- agement Science56.10 (2010), pp. 1833–1848

    work page 2010

  27. [27]

    Adaptive multilevel Monte Carlo for probabilities

    A.-L. Haji-Ali, J. Spence, and A. L. Teckentrup. “Adaptive multilevel Monte Carlo for probabilities”. In:SIAM Journal on Numerical Analysis60.4 (2022), pp. 2125–2149

    work page 2022

  28. [28]

    Hall and C

    P. Hall and C. C. Heyde. Martingale Limit Theory and Its Application. Academic Press New York, 1980

    work page 1980

  29. [29]

    Convergence rate of linear two-time-scale stochastic approximation

    V. R. Konda and J. N. Tsitsiklis. “Convergence rate of linear two-time-scale stochastic approximation”. In:The Annals of Applied Probability14.2 (2004), pp. 796–819

    work page 2004

  30. [30]

    Convergence rate and averaging of nonlinear two-time- scale stochastic approximation algorithms

    A. Mokkadem and M. Pelletier. “Convergence rate and averaging of nonlinear two-time- scale stochastic approximation algorithms”. In:The Annals of Applied Probability 16.3 (2006), pp. 1671–1702

    work page 2006

  31. [31]

    Acceleration of stochastic approximation by averaging

    B. T. Polyak and A. B. Juditsky. “Acceleration of stochastic approximation by averaging”. In: SIAM Journal on Control and Optimization30.4 (1992), pp. 838–855

    work page 1992

  32. [32]

    A stochastic approximation method

    H. Robbins and S. Monro. “A stochastic approximation method”. In:The Annals of Math- ematical Statistics22.3 (1951), pp. 400–407

    work page 1951

  33. [33]

    Optimization of conditional value-at-risk

    R. T. Rockafellar and S. Uryasev. “Optimization of conditional value-at-risk”. In:Journal of Risk 2.3 (2000), pp. 21–41

    work page 2000

  34. [34]

    Handbookofsequentialanalysis

    D.Ruppert.“Handbookofsequentialanalysis”.In: Stochastic Approximation(1991),pp.503– 529

    work page 1991

  35. [35]

    Swiss Federal Office of Private Insurance.The risk margin for the Swiss solvency test. 2004. url: finma.ch/FinmaArchiv/bpv/download/e/WhitePaperSST_en.pdf. 56

    work page 2004