Paper: arXiv 2311.15333
Authors: Stéphane Crépey, Noufel Frikha, Azar Louzi, Gilles Pagès
Abstract
Crépey, Frikha, and Louzi (2023) 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.
Complexity vs Empirical Score
- Math Complexity: 9.0/10
- Empirical Rigor: 4.0/10
- Quadrant: Lab Rats — high math complexity, limited empirical testing
Why this score: The paper is mathematically dense, featuring advanced stochastic approximation theory, multilevel Monte Carlo acceleration, and central limit theorems, while the empirical validation is limited to a single numerical example without code, backtests, or datasets.
Research Flowchart
flowchart TD A["Research Goal<br>Asymptotic Error Analysis<br>of Multilevel SA for VaR & ES"] --> B["Key Methodology<br>Nested Stochastic Approximation<br>Algorithm & Multilevel Acceleration"] B --> C["Data/Input<br>Random Financial Loss<br>Distributions"] C --> D["Computational Process<br>Renormalized Estimation Errors<br>Central Limit Theorems"] D --> E["Key Findings<br>CLTs for Standard & Multilevel SA<br>Validated by Numerical Example"]
Evidence Card
What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card
Proposes
The paper establishes central limit theorems for the renormalized estimation errors of nested stochastic approximation (NSA) and multilevel stochastic approximation (MLSA) algorithms, as well as for their Polyak‑Ruppert averaged versions.
Source sentence
We hereby establish central limit theorems for the renormalized estimation errors associated with both algorithms as well as their averaged versions.
Assumes 6
- For any bias parameter h, the cdf of X_h admits a first‑order Taylor expansion with remainder terms that vanish as h→0. statistical
Source sentence
(i) For any h ∈H, FXh admits the first order Taylor expansion FXh(ξ) −FX0(ξ) = v(ξ)h + w(ξ, h)h, ξ ∈R, for some functions v, w( · , h): R →R satisfying, for any ξ0 ⋆∈Argmin V0, Z ∞ ξ0⋆ v(ξ)dξ < ∞, lim H∋h↓0 w(ξ0 ⋆, h) = lim H∋h↓0 Z ∞ ξ0⋆ w(ξ, h)dξ = 0.
- For any h, the law of X_h has a continuous probability density function f_{X_h} that converges locally uniformly to f_{X_0}. statistical
Source sentence
(ii) For any h ∈H∪{0}, the law of Xh admits a continuous pdf fXh with respect to the Lebesgue measure. Moreover, the pdf {fXh, h ∈H} converge locally uniformly to fX0.
- The densities f_{X_h} are uniformly bounded and uniformly Lipschitz over h∈H∪{0}. statistical
Source sentence
(iv) The pdf {fXh, h ∈H ∪{0}} are uniformly bounded and uniformly Lipschitz, namely, sup h∈H∪{0} (∥fXh∥∞+ [fXh]Lip) < ∞, where [fXh]Lip denotes the Lipschitz constant of fXh, h ∈H ∪{0}. Remark 1.2.
- For any radius R, the densities f_{X_h} are uniformly positive on the ball B(ξ*_0,R). statistical
Source sentence
(iii) For any R > 0, inf h∈H∪{0} ξ∈B(ξ0 ⋆,R) fXh(ξ) > 0.
Show 2 more
- The bias parameter h satisfies sup_{ξ∈K}|f_{X_h}(ξ)-f_{X_0}(ξ)| ≤ C h^{1/4+δ_0} for any compact K. statistical
Source sentence
There exist positive constants C, δ0 < ∞such that, for any h ∈H and any compact set K ⊂R, sup ξ∈K |fXh(ξ) −fX0(ξ)| ≤Ch 1 4 +δ0.
- Learning rates are of the form γ_n = γ_1 n^{-β} with γ_1>0 and β∈(1/2,1]. execution
Source sentence
and advancing at the positive learning rate {γn, n ≥1} such that P∞ n=1 γn = ∞and P∞ n=1 γ2 n < ∞. Given a learning rate {γn = γ1n−β, n ≥1}, γ1 > 0, β ∈ � 1 2, 1 , this complexity is achieved by MLSA for β = 1 under the constraint λγ1 > 1, where the constant λ > 0 in (1.6) is explicit but tedious to compute.
Data
- Numerical case study synthetic unknown
Source sentence
Section 5 presents a numerical case study supporting the paper’s theoretical findings. The present article complements the aforementioned one by analyzing the corresponding asymptotic error distributions, as required for delimiting VaR and ES trust regions and confidence 19 intervals.
Costs
Not applicable
Finds 5
- Central limit theorems are proved for the renormalized errors of NSA, MLSA and their averaged counterparts. theoretical
Source sentence
We hereby establish central limit theorems for the renormalized estimation errors associated with both algorithms as well as their averaged versions. According to context, we use the notation Nℓ to designate both Nℓand Nℓ interchangeably. Theorem 3.5.
- A numerical example confirms the theoretical CLTs and shows the Gaussian fit of the renormalized (VaR, ES) errors. other
Source sentence
Our findings are substantiated through a numerical example. Figure 1 plots, for each algorithm, a 95%-confidence ellipse and Gaussian marginals of the joint distributions of the renormalized (VaR, ES) estimation errors.
- The multilevel scheme reduces computational complexity to O(ε^{-5/2}) for a prescribed accuracy ε. theoretical
Source sentence
For some prescribed accuracy ε > 0, the optimal complexity attained by the presented multilevel algorithms is in O(ε−5 2 ). Given a learning rate {γn = γ1n−β, n ≥1}, γ1 > 0, β ∈ � 1 2, 1 , this complexity is achieved by MLSA for β = 1 under the constraint λγ1 > 1, where the constant λ > 0 in (1.6) is explicit but tedious to compute.
- Averaged versions of the algorithms achieve better convergence rates and increased numerical stability compared to non‑averaged schemes. theoretical
Source sentence
To bypass this tuning issue, we explore the effect of the Polyak-Ruppert averaging principle [30, 18, 33] on the VaR NSA scheme. Further averaged extensions of these algorithms are also presented and shown to achieve better convergence rates than their original counterparts.
- Optimal complexity O(ε^{-5/2}) is also attained by the averaged MLSA (AMLSA) for β∈(8/9,1] without constraints on γ_1. theoretical
Source sentence
This complexity is also achieved by AMLSA for β ∈ � 8 9, 1 , without any constraint on γ1.
Checked by others
No other paper in the archive has been found to support or contradict these findings (compared with 19 related papers). Coverage is partial, so this is neither replication nor refutation.
Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.