pith. sign in

arxiv: 1906.08372 · v1 · pith:RSHF4ZC7new · submitted 2019-06-19 · 🧮 math.PR · math.ST· stat.TH

First order covariance inequalities via Stein's method

Marie Ernst , Gesine Reinert , Yvik Swan This is my paper

Pith reviewed 2026-05-25 19:47 UTC · model grok-4.3

classification 🧮 math.PR math.STstat.TH
keywords Stein's methodinverse Stein operatorscovariance identitiesStein kernelPoincaré inequalitiescovariance boundsunivariate distributionsCauchy-Schwarz
0
0 comments X

The pith

Probabilistic representations for inverse Stein operators yield new covariance identities and sharp bounds for any univariate target.

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

The paper develops probabilistic representations for inverse Stein operators that hold under general conditions for arbitrary univariate distributions. These representations supply explicit expressions for the Stein kernel and permit derivation of bounds on the solutions to Stein equations. The authors obtain covariance identities expressing the covariance between arbitrary functionals of the target random variable as a weighted covariance of the derivatives of those functionals, where the weights are given explicitly in terms of standard Stein objects. Applying the Cauchy-Schwarz inequality to the identities produces sharp upper and lower covariance bounds, which include weighted Poincaré inequalities. Several classical variance bounds appear as direct corollaries.

Core claim

Under general conditions, inverse Stein operators for an arbitrary univariate probability distribution admit probabilistic representations. These representations deliver simple expressions for the associated Stein kernel. The representations further yield covariance identities that write the covariance between two arbitrary functionals as a weighted covariance between their derivatives, with the weight depending on the target distribution. The Cauchy-Schwarz inequality applied to these identities then gives sharp covariance bounds, among them weighted Poincaré inequalities, and recovers known variance bounds of Klaassen, Brascamp-Lieb, and Otto-Menz as special cases.

What carries the argument

Probabilistic representations for inverse Stein operators, which solve the Stein equation and furnish the Stein kernel.

Load-bearing premise

Probabilistic representations for inverse Stein operators exist and remain valid under the stated general conditions for an arbitrary univariate target distribution.

What would settle it

A univariate distribution together with two functionals for which either no probabilistic representation of the inverse Stein operator exists or the claimed covariance identity fails to hold.

Figures

Figures reproduced from arXiv: 1906.08372 by Gesine Reinert, Marie Ernst, Yvik Swan.

Figure 1
Figure 1. Figure 1: The functions x 7→ K` p (x, x0 )/p(x) for different (fixed) values of x 0 and p the standard normal distribution (Figure 1a); beta distribution with parameters 1.3 and 2.4 (Figure 1b); gamma distribution with parameters 1.3 and 2.4 (Figure 1c); binomial distribution with parameters (50, 0.2) (Figure 1d); Poisson distribution with parameter 20 (Figure 1e); hypergeometric distribution with parameters 100, 50… view at source ↗
Figure 2
Figure 2. Figure 2: The functions x 7→ K` p (x, x)/p(x) for different parameter values p the standard normal distribution (Figure 2a); beta distribution (Figure 2b); gamma distribution (Figure 2c); binomial dis￾tribution with parameters (Figure 2d); Poisson distribution (Figure 2e); hypergeometric distribution (Figure 2f). 15 [PITH_FULL_IMAGE:figures/full_fig_p015_2.png] view at source ↗
read the original abstract

We propose probabilistic representations for inverse Stein operators (i.e. solutions to Stein equations) under general conditions; in particular we deduce new simple expressions for the Stein kernel. These representations allow to deduce uniform and non-uniform Stein factors (i.e. bounds on solutions to Stein equations) and lead to new covariance identities expressing the covariance between arbitrary functionals of an arbitrary {univariate} target in terms of a weighted covariance of the derivatives of the functionals. Our weights are explicit, easily computable in most cases, and expressed in terms of objects familiar within the context of Stein's method. Applications of the Cauchy-Schwarz inequality to these weighted covariance identities lead to sharp upper and lower covariance bounds and, in particular, weighted Poincar\'e inequalities. Many examples are given and, in particular, classical variance bounds due to Klaassen, Brascamp and Lieb or Otto and Menz are corollaries. Connections with more recent literature are also detailed.

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

3 major / 2 minor

Summary. The manuscript proposes probabilistic representations for inverse Stein operators (solutions to Stein equations) under general conditions for arbitrary univariate target distributions. These yield new simple expressions for the Stein kernel, uniform and non-uniform Stein factors, and covariance identities expressing cov(f(X), g(X)) for arbitrary functionals f, g in terms of a weighted covariance of f' and g'. Cauchy-Schwarz applied to the identities produces sharp upper and lower covariance bounds, including weighted Poincaré inequalities. Classical results (Klaassen, Brascamp-Lieb, Otto-Menz) are recovered as corollaries, with many examples and literature connections.

Significance. If the representations and identities hold under the stated generality, the paper supplies a unified, explicit framework for first-order covariance inequalities via Stein's method. The computable weights and recovery of sharp classical bounds as special cases would make the results useful for researchers working on concentration, variance bounds, and Stein's method applications. No machine-checked proofs or parameter-free derivations are claimed, but the approach to Stein factors is a clear strength.

major comments (3)
  1. [§2] §2 (main representation result, around Eq. (2.4)–(2.8)): The probabilistic representation for the inverse Stein operator and the resulting Stein kernel expression are derived under 'general conditions,' but the argument relies on integration against the target measure in a form that presupposes either a density or sufficient regularity to pass from the Stein equation solution to the weighted covariance identity. For atomic distributions the construction may require separate justification (sums instead of integrals), which is not explicitly supplied; this is load-bearing for the abstract's claim of validity for arbitrary univariate targets.
  2. [§4] §4 (covariance bounds and weighted Poincaré, Eq. (4.2)–(4.5)): The passage from the weighted covariance identity to the sharp bounds via Cauchy-Schwarz assumes the Stein kernel is well-defined and positive almost everywhere with respect to the target, together with integrability of the derivatives. No additional moment or support conditions are stated beyond the 'general conditions,' yet the claimed generality of the resulting Poincaré-type inequalities for targets lacking densities or with atoms rests on this unverified extension.
  3. [§3.2] §3.2 (covariance identity, Theorem 3.1): The identity cov(f(X),g(X)) = E[w(X) f'(X) g'(X)] (with w the Stein kernel) is presented as holding for arbitrary functionals; the proof sketch does not address boundary cases where the target is discrete, where the representation of the inverse operator may fail to produce a usable weight without extra regularity. This directly affects the scope of all subsequent corollaries.
minor comments (2)
  1. [Notation] Notation for the Stein operator T and kernel is mostly consistent, but the transition between the representation in §2 and its use in the covariance identity in §3 would benefit from an explicit reminder of the domain of the functionals.
  2. [§5] A few examples in §5 are continuous; adding one fully discrete atomic example would help readers verify the claimed generality without altering the main results.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for the careful and constructive report. The comments focus on the scope of our results for atomic distributions, and we address each point below with plans for clarification in the revision.

read point-by-point responses

  1. Referee: [§2] §2 (main representation result, around Eq. (2.4)–(2.8)): The probabilistic representation for the inverse Stein operator and the resulting Stein kernel expression are derived under 'general conditions,' but the argument relies on integration against the target measure in a form that presupposes either a density or sufficient regularity to pass from the Stein equation solution to the weighted covariance identity. For atomic distributions the construction may require separate justification (sums instead of integrals), which is not explicitly supplied; this is load-bearing for the abstract's claim of validity for arbitrary univariate targets.

    Authors: We agree that the derivation in Section 2 is presented using integrals and does not explicitly treat the atomic case. In the revision we will add a short paragraph after the main representation result noting that the same argument applies verbatim to atomic targets upon replacing integrals by sums (i.e., expectations with respect to the counting measure), under the identical general conditions on the Stein operator. This makes the claim for arbitrary univariate targets fully rigorous without changing any statements or proofs. revision: yes

  2. Referee: [§4] §4 (covariance bounds and weighted Poincaré, Eq. (4.2)–(4.5)): The passage from the weighted covariance identity to the sharp bounds via Cauchy-Schwarz assumes the Stein kernel is well-defined and positive almost everywhere with respect to the target, together with integrability of the derivatives. No additional moment or support conditions are stated beyond the 'general conditions,' yet the claimed generality of the resulting Poincaré-type inequalities for targets lacking densities or with atoms rests on this unverified extension.

    Authors: The positivity and integrability of the Stein kernel follow directly from its explicit representation in Section 2 once the general conditions are satisfied. We will insert a brief verification paragraph in Section 4 confirming that these properties continue to hold when the target is atomic (again replacing integrals by sums), thereby justifying the application of Cauchy-Schwarz and the resulting weighted Poincaré inequalities in full generality. revision: yes

  3. Referee: [§3.2] §3.2 (covariance identity, Theorem 3.1): The identity cov(f(X),g(X)) = E[w(X) f'(X) g'(X)] (with w the Stein kernel) is presented as holding for arbitrary functionals; the proof sketch does not address boundary cases where the target is discrete, where the representation of the inverse operator may fail to produce a usable weight without extra regularity. This directly affects the scope of all subsequent corollaries.

    Authors: Theorem 3.1 is proved from the representation in Section 2. We will augment the proof sketch with a single sentence observing that the argument is measure-theoretic and therefore carries over to discrete targets by interpreting all expectations as sums; the resulting weight remains well-defined and the identity holds for arbitrary (sufficiently differentiable) functionals. The corollaries are consequently unaffected. revision: yes

Circularity Check

0 steps flagged

No circularity; derivations start from new probabilistic representations and proceed independently

full rationale

The paper proposes new probabilistic representations for inverse Stein operators and Stein kernels under stated general conditions for univariate targets. From these representations it derives Stein factors, then covariance identities expressing cov(f,g) in terms of weighted cov of derivatives, then applies Cauchy-Schwarz to obtain bounds and weighted Poincaré inequalities. Classical results (Klaassen, Brascamp-Lieb, Otto-Menz) appear only as corollaries recovered after the new identities are established. No step reduces a claimed prediction or identity to a fitted parameter or to a self-citation whose content is the target result itself. The central objects (representations, kernels, weights) are constructed explicitly from the target distribution and are not defined in terms of the final bounds. Self-citations, if present, are not load-bearing for the main identities. The derivation chain is therefore self-contained against external benchmarks.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The paper invokes general conditions under which inverse Stein operators admit probabilistic representations; no numerical free parameters, ad-hoc constants, or newly postulated entities are mentioned.

axioms (1)
  • domain assumption Inverse Stein operators admit probabilistic representations under general conditions for arbitrary univariate targets.
    The entire development of new expressions, identities, and bounds rests on this premise stated in the abstract.

pith-pipeline@v0.9.0 · 5689 in / 1231 out tokens · 29188 ms · 2026-05-25T19:47:48.620460+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

71 extracted references · 71 canonical work pages · 7 internal anchors

  1. [1]

    Afendras and N

    G. Afendras and N. Papadatos. On matrix variance inequalities. Journal of Statistical Planning and Inference, 141(11):3628–3631, 2011

    work page 2011

  2. [2]

    Afendras, N

    G. Afendras, N. Papadatos, and V. Papathanasiou. The discrete Mohr and Noll inequality with applications to variance bounds. Sankhy¯ a, 69(2):162–189, 2007

    work page 2007

  3. [3]

    Afendras and V

    G. Afendras and V. Papathanasiou. A note on a variance bound for the multinomial and the negative multinomial distribution. Naval Research Logistics (NRL), 61(3):179–183, 2014

    work page 2014

  4. [4]

    On Stein's Method for Infinitely Divisible Laws With Finite First Moment

    B. Arras and C. Houdr´ e. On Stein’s method for infinitely divisible laws with finite first moment. arXiv preprint arXiv:1712.10051 , 2017

    work page internal anchor Pith review Pith/arXiv arXiv 2017

  5. [5]

    On Stein's Method for Multivariate Self-Decomposable Laws With Finite First Moment

    B. Arras and C. Houdr´ e. On Stein’s method for multivariate self-decomposable laws with finite first moment. arXiv preprint arXiv:1809.02050 , 2018

    work page internal anchor Pith review Pith/arXiv arXiv 2018

  6. [6]

    Barbour, M

    A. Barbour, M. J. Luczak, A. Xia, et al. Multivariate approximation in total variation, ii: Discrete normal approximation. The Annals of Probability , 46(3):1405–1440, 2018

    work page 2018

  7. [7]

    A. D. Barbour and L. H. Y. Chen. An introduction to Stein’s method , volume 4 of Lect. Notes Ser. Inst. Math. Sci. Natl. Univ. Singap. Singapore University Press, Singapore, 2005

    work page 2005

  8. [8]

    A. D. Barbour and L. H. Y. Chen. Stein’s method and applications, volume 5 of Lect. Notes Ser. Inst. Math. Sci. Natl. Univ. Singap. Singapore University Press, Singapore, 2005

    work page 2005

  9. [9]

    ´A. Baricz. Mills’ ratio: monotonicity patterns and functional inequalities.Journal of Mathematical Analysis and Applications, 340(2):1362–1370, 2008

    work page 2008

  10. [10]

    Borovkov and S

    A. Borovkov and S. Utev. On an inequality and a related characterization of the normal distri- bution. Theory of Probability & Its Applications , 28(2):219–228, 1984

    work page 1984

  11. [11]

    H. J. Brascamp and E. H. Lieb. On extensions of the Brunn-Minkowski and Pr´ ekopa-Leindler theorems, including inequalities for log concave functions, and with an application to the diffusion equation. Journal of Functional Analysis , 22(4):366–389, 1976

    work page 1976

  12. [12]

    Cacoullos

    T. Cacoullos. On upper and lower bounds for the variance of a function of a random variable. The Annals of Probability , 10(3):799–809, 1982

    work page 1982

  13. [13]

    Cacoullos, N

    T. Cacoullos, N. Papadatos, and V. Papathanasiou. Variance inequalities for covariance kernels and applications to central limit theorems. Theory of Probability & Its Applications , 42(1):149– 155, 1998

    work page 1998

  14. [14]

    Cacoullos and V

    T. Cacoullos and V. Papathanasiou. On upper and lower bounds for the variance of functions of a random variable. Statistics & Probability Letters , 3:175–184, 1985. 24 name p.m.f. p(x) Stein kernel τℓ(x) parameter support Cum. Ord relation Poisson (λ) e−λλx/x! τ−(x) =λ λ> 0 x = 0, 1,... τ +(x) =x (δ,β,γ ) = (0, 0,λ ) Stein operators A+ Poi(λ)g(x) = (x−λ)g...

    work page 1985

  15. [15]

    Cacoullos and V

    T. Cacoullos and V. Papathanasiou. Bounds for the variance of functions of random variables by orthogonal polynomials and Bhattacharyya bounds. Statistics & Probability Letters , 4(1):21–23, 1986

    work page 1986

  16. [16]

    Cacoullos and V

    T. Cacoullos and V. Papathanasiou. Characterizations of distributions by variance bounds. Statis- tics & Probability Letters , 7(5):351–356, 1989

    work page 1989

  17. [17]

    Cacoullos and V

    T. Cacoullos and V. Papathanasiou. Lower variance bounds and a new proof of the central limit theorem. Journal of Multivariate Analysis , 43(2):173–184, 1992

    work page 1992

  18. [18]

    Cacoullos and V

    T. Cacoullos and V. Papathanasiou. A generalization of covariance identity and related charac- terizations. Mathematical Methods of Statistics , 4(1):106–113, 1995

    work page 1995

  19. [19]

    E. A. Carlen, D. Cordero-Erausquin, and E. H. Lieb. Asymmetric covariance estimates of Brascamp–Lieb type and related inequalities for log-concave measures. Annales de l’Institut Henri Poincar´ e, Probabilit´ es et Statistiques, 49:1–12, 2013

    work page 2013

  20. [20]

    Chang and D

    W.-Y. Chang and D. S. P. Richards. Variance inequalities for functions of multivariate random variables. Advances in Stochastic Inequalities: AMS Special Session on Stochastic Inequalities and Their Applications, October 17-19, 1997, Georgia Institute of Technology , 234:43, 1999

    work page 1997

  21. [21]

    A short survey of Stein's method

    S. Chatterjee. A short survey of Stein’s method. Preprint arXiv:1404.1392, 2014

    work page internal anchor Pith review Pith/arXiv arXiv 2014

  22. [22]

    Chatterjee and Q.-M

    S. Chatterjee and Q.-M. Shao. Nonnormal approximation by Stein’s method of exchangeable pairs with application to the Curie-Weiss model. The Annals of Applied Probability , 21(2):464–483, 2011

    work page 2011

  23. [23]

    L. H. Chen. An inequality for the multivariate normal distribution. Journal of Multivariate Analysis, 12(2):306–315, 1982

    work page 1982

  24. [24]

    L. H. Chen. Poincar´ e-type inequalities via stochastic integrals.Zeitschrift f¨ ur Wahrscheinlichkeit- stheorie und Verwandte Gebiete , 69(2):251–277, 1985

    work page 1985

  25. [25]

    L. H. Y. Chen. Poisson approximation for dependent trials. The Annals of Probability , 3(3):534– 545, 1975

    work page 1975

  26. [26]

    L. H. Y. Chen, L. Goldstein, and Q.-M. Shao. Normal approximation by Stein’s method . Proba- bility and its Applications (New York). Springer, Heidelberg, 2011

    work page 2011

  27. [27]

    H. Chernoff. The identification of an element of a large population in the presence of noise. The Annals of Statistics , 8(6):1179–1197, 1980

    work page 1980

  28. [28]

    T. A. Courtade, M. Fathi, and A. Pananjady. Existence of Stein kernels under a spectral gap, and discrepancy bound. arXiv preprint arXiv:1703.07707 , 2017

    work page internal anchor Pith review Pith/arXiv arXiv 2017

  29. [29]

    C. M. Cuadras. On the covariance between functions. Journal of Multivariate Analysis , 81(1):19– 27, 2002

    work page 2002

  30. [30]

    Diaconis and S

    P. Diaconis and S. Zabell. Closed form summation for classical distributions: variations on a theme of de Moivre. Statistical Science, 6(3):284–302, 1991

    work page 1991

  31. [31]

    D¨ obler

    C. D¨ obler. Stein’s method of exchangeable pairs for the Beta distribution and generalizations. Electronic Journal of Probability, 20(109):1–34, 2015

    work page 2015

  32. [32]

    W. Ehm. Binomial approximation to the poisson binomial distribution. Statistics & Probability Letters, 11(1):7–16, 1991. 28

    work page 1991

  33. [33]

    Ernst, G

    M. Ernst, G. Reinert, and Y. Swan. Papathanasiou and Olkin-Shepp–type expansions for uni- variate target distributions. 2019

    work page 2019

  34. [34]

    Fang, Q.-M

    X. Fang, Q.-M. Shao, and L. Xu. Multivariate approximations in Wasserstein distance by Stein’s method and bismut’s formula. Probability Theory and Related Fields , pages 1–35, 2018

    work page 2018

  35. [35]

    M. Fathi. Higher-Order Stein kernels for Gaussian approximation. arXiv preprint arXiv:1812.02703, 2018

    work page internal anchor Pith review Pith/arXiv arXiv 2018

  36. [36]

    M. Fathi. Stein kernels and moment maps. arXiv preprint arXiv:1804.04699 , 2018

    work page arXiv 2018

  37. [37]

    Goldstein and G

    L. Goldstein and G. Reinert. Stein’s method for the Beta distribution and the P´ olya-Eggenberger urn. Journal of Applied Probability , 50(4):1187–1205, 2013

    work page 2013

  38. [38]

    Gorham, A

    J. Gorham, A. B. Duncan, S. J. Vollmer, and L. Mackey. Measuring sample quality with diffusions. The Annals of Applied Probability (to appear) , 2019

    work page 2019

  39. [39]

    Gorham and L

    J. Gorham and L. Mackey. Measuring sample quality with kernels. In Proceedings of the 34th International Conference on Machine Learning-Volume 70 , pages 1292–1301. JMLR. org, 2017

    work page 2017

  40. [40]

    Hillion, O

    E. Hillion, O. Johnson, and Y. Yu. A natural derivative on [0 ,n ] and a binomial Poincar´ e inequality. ESAIM: Probability and Statistics , 18:703–712, 2014

    work page 2014

  41. [41]

    H¨ offding

    W. H¨ offding. Masstabinvariante Korrelationstheorie.Schriften des Mathematischen Instituts und Instituts fur Angewandte Mathematik der Universit¨ at Berlin, 5:181–233, 1940

    work page 1940

  42. [42]

    H¨ offding.The collected works of Wassily Hoeffding

    W. H¨ offding.The collected works of Wassily Hoeffding. Springer Science & Business Media, 2012

    work page 2012

  43. [43]

    S. Holmes. Stein’s method for birth and death chains. In Stein’s method: expository lectures and applications, volume 46 of IMS Lecture Notes Monogr. Ser. , pages 45–67. Inst. Math. Statist., Beachwood, OH, 2004

    work page 2004

  44. [44]

    S. Karlin. A general class of variance inequalities. Multivariate Analysis: Future Directions, Elsevier Science Publishers, New York , pages 279–294, 1993

    work page 1993

  45. [45]

    C. A. J. Klaassen. On an inequality of Chernoff. The Annals of Probability , 13(3):966–974, 1985

    work page 1985

  46. [46]

    R. Korwar. On characterizations of distributions by mean absolute deviation and variance bounds. Annals of the Institute of Statistical Mathematics , 43(2):287–295, 1991

    work page 1991

  47. [47]

    Kusuoka and C

    S. Kusuoka and C. A. Tudor. Stein’s method for invariant measures of diffusions via Malliavin calculus. Stochastic Processes and their Applications , 122(4):1627–1651, 2012

    work page 2012

  48. [48]

    Landsman, S

    Z. Landsman, S. Vanduffel, and J. Yao. A note on Stein’s lemma for multivariate elliptical distributions. Journal of Statistical Planning and Inference , 143(11):2016–2022, 2013

    work page 2016

  49. [49]

    Landsman, S

    Z. Landsman, S. Vanduffel, and J. Yao. Some Stein-type inequalities for multivariate elliptical distributions and applications. Statistics & Probability Letters , 97:54–62, 2015

    work page 2015

  50. [50]

    C. Ley, G. Reinert, and Y. Swan. Distances between nested densities and a measure of the impact of the prior in Bayesian statistics. Annals of Applied Probability, 27(1):216–241, 2016

    work page 2016

  51. [51]

    Ley and Y

    C. Ley and Y. Swan. Stein’s density approach and information inequalities. Electronic Commu- nications in Probability, 18(7):1–14, 2013

    work page 2013

  52. [52]

    Ley and Y

    C. Ley and Y. Swan. Parametric Stein operators and variance bounds. Brazilian Journal of Probability and Statistics, 30:171–195, 2016. 29

    work page 2016

  53. [53]

    C. Ley, Y. Swan, and G. Reinert. Stein’s method for comparison of univariate distributions. Probability Surveys, 14:1–52, 2017

    work page 2017

  54. [54]

    Mackey and J

    L. Mackey and J. Gorham. Multivariate Stein factors for a class of strongly log-concave distribu- tions. Electronic Communications in Probability, 21, 2016

    work page 2016

  55. [55]

    Menz and F

    G. Menz and F. Otto. Uniform logarithmic sobolev inequalities for conservative spin systems with super-quadratic single-site potential. The Annals of Probability , 41(3B):2182–2224, 2013

    work page 2013

  56. [56]

    J. Nash. Continuity of solutions of parabolic and elliptic equations. The American Journal of Mathematics, 80:931–954, 1958

    work page 1958

  57. [57]

    Nourdin and G

    I. Nourdin and G. Peccati. Normal approximations with Malliavin calculus : from Stein’s method to universality. Cambridge Tracts in Mathematics. Cambridge University Press, 2012

    work page 2012

  58. [58]

    Papathanasiou

    V. Papathanasiou. A characterization of the Pearson system of distributions and the associated orthogonal polynomials. Annals of the Institute of Statistical Mathematics , 47(1):171–176, 1995

    work page 1995

  59. [59]

    B. P. Rao. Matrix variance inequalities for multivariate distributions. Statistical Methodology, 3(4):416–430, 2006

    work page 2006

  60. [60]

    G. Reinert. A weak law of large numbers for empirical measures via stein’s method. The Annals of Probability, pages 334–354, 1995

    work page 1995

  61. [61]

    G. Reinert. Three general approaches to Stein’s method. In An introduction to Stein’s method , volume 4. Lecture Notes Series, Institute for Mathematical Sciences, National University of Sin- gapore, 2004

    work page 2004

  62. [62]

    Reinert, G

    G. Reinert, G. Mijoule, and Y. Swan. Stein gradients and divergences for multivariate continuous distributions. arXiv:1806.03478, 2018

    work page arXiv 2018

  63. [63]

    N. Ross. Fundamentals of Stein’s method. Probability Surveys, 8:210–293, 2011

    work page 2011

  64. [64]

    A. Saumard. Weighted Poincar´ e inequalities, concentration inequalities and tail bounds related to the behavior of the Stein kernel in dimension one. arXiv preprint arXiv:1804.03926 , 2018

    work page internal anchor Pith review Pith/arXiv arXiv 2018

  65. [65]

    On the isoperimetric constant, covariance inequalities and $L_p$-Poincar\'{e} inequalities in dimension one

    A. Saumard and J. A. Wellner. On the Isoperimetric constant, covariance inequalities and Lp- Poincar´ e inequalities in dimension one.arXiv preprint arXiv:1711.00668 , 2017

    work page internal anchor Pith review Pith/arXiv arXiv 2017

  66. [66]

    Saumard and J

    A. Saumard and J. A. Wellner. Efron’s monotonicity property for measures on R2. Journal of Multivariate Analysis, 166:212–224, 2018

    work page 2018

  67. [67]

    Schoutens

    W. Schoutens. Orthogonal polynomials in Stein’s method. Journal of Mathematical Analysis and Applications, 253(2):515–531, 2001

    work page 2001

  68. [68]

    S. Y. Soon. Binomial approximation for dependent indicators. Statistica Sinica, 6(3):703–714, 1996

    work page 1996

  69. [69]

    C. Stein. A bound for the error in the normal approximation to the distribution of a sum of dependent random variables. In Proceedings of the Sixth Berkeley Symposium on Mathematical Statistics and Probability (Univ. California, Berkeley, Calif., 1970/1971), Vol. II: Probability theory, pages 583–602, Berkeley, Calif., 1972. Univ. California Press

    work page 1970

  70. [70]

    C. Stein. Approximate computation of expectations. Institute of Mathematical Statistics Lecture Notes—Monograph Series, 7. Institute of Mathematical Statistics, Hayward, CA, 1986

    work page 1986

  71. [71]

    Upadhye, V

    N. Upadhye, V. Cekanavicius, and P. Vellaisamy. On Stein operators for discrete approximations. Bernoulli, 23(4A):2828–2859, 2017. 30 A Proofs from Section 2.3 Proof of Proposition 2.25. In order for (2.4) to hold we need (i) f(·)g(·− ℓ) ∈ F(1) ℓ (p) and (ii) f(·)∆−ℓg(·) ∈ L1(p). Condition (ii) is satisfied under (2.23). By definition of F(1) ℓ (p), conditi...

    work page 2017