arxiv: 2604.05234 · v1 · submitted 2026-04-06 · 🧮 math.PR · math-ph· math.MP

Recognition: 2 theorem links

· Lean Theorem

Quantitative propagation of chaos and universality for asymmetric Langevin spin glass dynamics

Manuel Arnese , Kevin Hu

Authors on Pith no claims yet

Pith reviewed 2026-05-10 18:34 UTC · model grok-4.3

classification 🧮 math.PR math-phmath.MP

keywords propagation of chaosLangevin spin glassesMcKean-Vlasov limitsWasserstein distanceT2 inequalityconcentration of measurequenched estimatesasymmetric interactions

0 comments

The pith

Langevin spin glass dynamics converge quantitatively to a McKean-Vlasov limit when the disorder satisfies the T2 inequality.

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

The paper establishes explicit rates for how the law of a single spin in asymmetric Langevin spin glass dynamics approaches a deterministic mean-field limit. Previous results showed only qualitative convergence for Gaussian disorder; here the authors extend this to i.i.d. disorders obeying the T2 inequality, obtaining rates in expected Wasserstein distance together with quantitative concentration bounds for Lipschitz observables. The estimates matter because they supply concrete error control when replacing large finite systems by their infinite-particle approximations in models of interacting particles.

Core claim

For Langevin spin glass dynamics with asymmetric interactions and i.i.d. disorder satisfying the T2 inequality, the quenched law of one spin converges in expected Wasserstein distance to the solution of the associated McKean-Vlasov equation at explicit rates, while Lipschitz functions of the spins satisfy quantitative concentration inequalities. The argument proceeds by coupling the finite-particle system to the mean-field limit and applying concentration-of-measure estimates, filtering techniques, and Malliavin calculus to control the non-Gaussian disorder.

What carries the argument

Coupling of the N-particle Langevin system to the McKean-Vlasov limit, combined with the T2 inequality on the disorder to produce rate bounds.

If this is right

The McKean-Vlasov equation can approximate the original finite-N dynamics with explicit error bounds that depend on system size.
The limiting behavior is the same for every disorder distribution obeying T2, including asymmetric interaction cases.
Quantitative concentration of Lipschitz observables supplies variance bounds useful for Monte Carlo estimation of spin-glass observables.
The coupling construction yields a practical way to compare finite-particle trajectories with the mean-field flow.

Where Pith is reading between the lines

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

The same coupling-plus-concentration strategy could be tested on other mean-field particle systems whose coefficients are random but satisfy a uniform concentration property.
If the T2 assumption is dropped, slower rates or additional logarithmic factors may appear, suggesting a natural next calculation.
The filtering-theory step points toward possible extensions that incorporate partial observations of the spins.
Error rates of this form could guide step-size choices in numerical schemes for sampling or optimization on spin-glass energy landscapes.

Load-bearing premise

The i.i.d. disorder satisfies the T2 inequality, which supplies the concentration needed to turn qualitative convergence into quantitative rates.

What would settle it

A concrete disorder distribution that violates T2, such as one with sufficiently heavy tails, for which the expected Wasserstein distance to the McKean-Vlasov limit fails to decay at the predicted speed.

read the original abstract

We obtain quantitative estimates on quenched propagation of chaos for Langevin spin glass dynamics with i.i.d. disorder. Prior work in the case of Gaussian disorder established the qualitative convergence of the law of a single spin to a deterministic McKean-Vlasov limit. We prove convergence rates in expected Wasserstein distance and quantitative concentration rates for Lipschitz observables under the assumption that the disorder satisfies the T2 inequality. The proof uses a coupling argument, together with techniques from concentration of measure, filtering theory, and Malliavin calculus

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.

Desk Editor's Note private letter to a colleague

This paper supplies explicit Wasserstein rates and concentration bounds for propagation of chaos in asymmetric Langevin spin-glass dynamics under a T2 assumption on the disorder.

read the letter

The core contribution is quantitative quenched propagation of chaos for these dynamics. Earlier work had only qualitative convergence to the McKean-Vlasov limit when the disorder is Gaussian; here they obtain rates in expected Wasserstein distance plus concentration for Lipschitz observables, and they extend the setting to i.i.d. disorder obeying T2 and to asymmetric interactions. The proof sketch combines coupling with concentration of measure, filtering, and Malliavin calculus, which matches the tools needed for the problem. That combination is a reasonable way to turn qualitative arguments into explicit bounds, and the abstract states the assumptions cleanly. If the full estimates close without large hidden constants or dimension blow-up, the work gives usable error control for mean-field approximations in disordered systems. The T2 condition is presented up front as the price for quantitative results, so there is no circularity or over-claim on that point. A minor limitation is that T2 is stronger than mere sub-Gaussian tails, so the results do not cover every i.i.d. disorder one might encounter in applications; that is stated explicitly rather than hidden. The rates themselves are not claimed to be sharp, which is fine for a first quantitative paper. The citation pattern looks standard for the area. This is aimed at probabilists working on mean-field limits, spin glasses, or high-dimensional stochastic optimization. Anyone who needs concrete error bounds when replacing the full system by its limit will find the explicit Wasserstein and concentration statements useful. The paper shows clear thinking on how to upgrade existing qualitative results, so it merits a serious referee even if the constants turn out to be large or the asymmetry handling requires extra care in the details. I would send it to peer review.

Referee Report

1 major / 2 minor

Summary. The paper establishes quantitative quenched propagation of chaos for asymmetric Langevin spin glass dynamics with i.i.d. disorder. Building on prior qualitative convergence results for Gaussian disorder to a deterministic McKean-Vlasov limit, it derives explicit convergence rates in expected Wasserstein distance and quantitative concentration bounds for Lipschitz observables, under the assumption that the disorder satisfies the T2 inequality. The proof relies on a coupling construction combined with concentration of measure, filtering theory, and Malliavin calculus.

Significance. If the estimates hold, the result is significant for providing the first quantitative rates in this setting under a general T2 assumption on the disorder, rather than restricting to Gaussian cases. This broadens applicability to a wider class of spin glass models while clearly identifying the enabling concentration condition. The use of Malliavin calculus and filtering for rate extraction is a technical strength, and the explicit separation of qualitative vs. quantitative regimes via the T2 hypothesis aids clarity in the mean-field limit literature.

major comments (1)

[Abstract / Introduction] The abstract states that rates are obtained under the T2 assumption on the disorder, but without the full text it is unclear whether the T2 inequality is used only for concentration or whether it enters the coupling construction in a way that affects the Wasserstein rate; a precise statement of how the constant in the rate depends on the T2 constant would strengthen the claim.

minor comments (2)

[Introduction] Ensure that the title's reference to 'asymmetric' dynamics is consistently explained in the introduction and that any asymmetry in the interaction or noise is explicitly used or shown to be inessential for the propagation-of-chaos argument.
[Abstract] The abstract mentions 'quenched' propagation of chaos; confirm that all stated rates are indeed quenched (i.e., hold for almost every realization of the disorder) and that the expectation is only over the initial conditions or the dynamics.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the careful reading of the manuscript and the positive recommendation for minor revision. We address the major comment below.

read point-by-point responses

Referee: [Abstract / Introduction] The abstract states that rates are obtained under the T2 assumption on the disorder, but without the full text it is unclear whether the T2 inequality is used only for concentration or whether it enters the coupling construction in a way that affects the Wasserstein rate; a precise statement of how the constant in the rate depends on the T2 constant would strengthen the claim.

Authors: We appreciate this suggestion for improved clarity. The T2 inequality is invoked in two places: (i) to obtain the quantitative concentration bounds for Lipschitz observables via standard concentration-of-measure arguments, and (ii) inside the coupling construction to control the discrepancy between the empirical measure and its McKean-Vlasov limit when the disorder is non-Gaussian. Consequently the constant appearing in the expected Wasserstein-distance bound depends linearly on the T2 constant of the disorder law. In the revised manuscript we will add an explicit statement of this dependence both in the introduction and in the statement of the main theorem (Theorem 1.1), together with a short remark explaining where T2 enters the estimates. revision: yes

Circularity Check

0 steps flagged

No significant circularity

full rationale

The derivation relies on an explicit external assumption (disorder satisfies T2 inequality) combined with standard analytic tools: coupling construction, concentration of measure, filtering theory, and Malliavin calculus. These are independent of the target result and do not reduce any claimed prediction or rate to a fitted parameter, self-definition, or self-citation chain. No load-bearing step equates the output to the input by construction, and the quantitative estimates are obtained under stated assumptions rather than by renaming or smuggling an ansatz.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The central claim rests on the T2 inequality for the disorder distribution and standard properties of Wasserstein distance, Malliavin calculus, and coupling arguments in stochastic analysis.

axioms (1)

domain assumption The disorder measure satisfies the T2 inequality
Invoked to obtain quantitative concentration and Wasserstein rates via concentration-of-measure techniques.

pith-pipeline@v0.9.0 · 5375 in / 1194 out tokens · 47520 ms · 2026-05-10T18:34:42.810346+00:00 · methodology

discussion (0)

Lean theorems connected to this paper

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

IndisputableMonolith/Foundation/AbsoluteFloorClosure.lean absolute_floor_iff_bare_distinguishability unclear

?

unclear
Relation between the paper passage and the cited Recognition theorem.

the entries of J ... satisfy a T2 inequality with constant σ²

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

80 extracted references · 12 canonical work pages · 2 internal anchors

[1]

Arnese and D

M. Arnese and D. Lacker,Sharp propagation of chaos for mean field Langevin dynamics, control, and games, arXiv preprint arXiv:2603.10988 (2026), available at2603.10988. QUANTITATIVE PROPAGATION OF CHAOS AND UNIVERSALITY FOR LANGEVIN SPIN GLASS 49

work page arXiv 2026
[2]

Ayi and N

N. Ayi and N. P. Duteil,Large-population limits of non-exchangeable particle systems, Active Particles, Volume 4: Theory, Models, Applications (2024), 79–133

2024
[3]

Basak and S

A. Basak and S. Mukherjee,Universality of the mean-field for the Potts model, Probab. Theory Related Fields168 (2017), no. 3-4, 557–600. MR3663625

2017
[4]

Bayraktar, S

E. Bayraktar, S. Chakraborty, and R. Wu,Graphon mean field systems, Ann. Appl. Probab.33(2023), no. 5, 3587–

2023
[5]

Bayraktar and R

E. Bayraktar and R. Wu,Stationarity and uniform in time convergence for the graphon particle system, Stochastic Process. Appl.150(2022), 532–568. MR4426164

2022
[6]

Ben Arous, A

G. Ben Arous, A. Dembo, and A. Guionnet,Aging of spherical spin glasses, Probab. Theory Related Fields120 (2001), no. 1, 1–67. MR1856194

2001
[7]

Ben Arous and A

G. Ben Arous and A. Guionnet,Large deviations for Langevin spin glass dynamics, Probab. Theory Related Fields 102(1995), no. 4, 455–509. MR1346262

1995
[8]

Probab.25(1997), no

,Symmetric Langevin spin glass dynamics, Ann. Probab.25(1997), no. 3, 1367–1422. MR1457623

1997
[9]

Ben Arous and O

G. Ben Arous and O. Zeitouni,Increasing propagation of chaos for mean field models, Ann. Inst. H. Poincar´ e Probab. Statist.35(1999), no. 1, 85–102. MR1669916

1999
[10]

Ben Arous, A

G. Ben Arous, A. Dembo, and A. Guionnet,Cugliandolo-Kurchan equations for dynamics of spin-glasses, Probab. Theory Related Fields136(2006), no. 4, 619–660. MR2257139

2006
[11]

Ben Arous, C

G. Ben Arous, C. Gerbelot, and V. Piccolo,Langevin dynamics for high-dimensional optimization: the case of multi- spiked tensor PCA, arXiv preprint arXiv:2408.06401 (2024), available at2408.06401

work page arXiv 2024
[12]

Ben Arous, R

G. Ben Arous, R. Gheissari, and A. Jagannath,Algorithmic thresholds for tensor PCA, Ann. Probab.48(2020), no. 4, 2052–2087. MR4124533

2020
[13]

,Bounding flows for spherical spin glass dynamics, Comm. Math. Phys.373(2020), no. 3, 1011–1048. MR4061404

2020
[14]

Bhamidi, A

S. Bhamidi, A. Budhiraja, and R. Wu,Weakly interacting particle systems on inhomogeneous random graphs, Sto- chastic Process. Appl.129(2019), no. 6, 2174–2206. MR3958427

2019
[15]

S. G. Bobkov, P. Nayar, and P. Tetali,Concentration properties of restricted measures with applications to non- Lipschitz functions, Geometric aspects of functional analysis, 2017, pp. 25–53. MR3645113

2017
[16]

Brunick and S

G. Brunick and S. Shreve,Mimicking an Itˆ o process by a solution of a stochastic differential equation, Ann. Appl. Probab.23(2013), no. 4, 1584–1628. MR3098443

2013
[17]

Carlen and P

E. Carlen and P. Kr´ ee,L p estimates on iterated stochastic integrals, Ann. Probab.19(1991), no. 1, 354–368. MR1085341

1991
[18]

P Cattiaux and A Guillin,Semi log-concave Markov diffusions, Lecture notes in mathematics, 2014, pp. 231–292

2014
[19]

The high-dimensional asymptotics of first order methods with random data

M. Celentano, C. Cheng, and A. Montanari,The high-dimensional asymptotics of first order methods with random data, arXiv preprint arXiv:2112.07572 (2025), available at2112.07572

work page internal anchor Pith review Pith/arXiv arXiv 2025
[20]

arXiv preprint arXiv:2603.18168 , year=

L.-P. Chaintron, L. Chizat, and J. Maass,Resnets of all shapes and sizes: Convergence of training dynamics in the large-scale limit, arXiv preprint arXiv:2603.18168 (2026), available at2603.18168

work page arXiv 2026
[21]

Chaintron and A

L.-P. Chaintron and A. Diez,Propagation of chaos: a review of models, methods and applications. I. Models and methods, Kinet. Relat. Models15(2022), no. 6, 895–1015. MR4489768

2022
[22]

,Propagation of chaos: a review of models, methods and applications. II. Applications, Kinet. Relat. Models 15(2022), no. 6, 1017–1173. MR4489769

2022
[23]

Chewi,Log-concave sampling

S. Chewi,Log-concave sampling. Book draft, version of March 18, 2026

2026
[24]

Chewi, J

S. Chewi, J. Niles-Weed, and P. Rigollet,Statistical optimal transport, Lecture Notes in Mathematics, vol. 2364, Springer, Cham, [2025]©2025. ´Ecole d’´Et´ e de Probabilit´ es de Saint-Flour XLIX—2019,´Ecole d’´Et´ e de Probabilit´ es de Saint-Flour. [Saint-Flour Probability Summer School]. MR4901218

2025
[25]

Coppini, H

F. Coppini, H. Dietert, and G. Giacomin,A law of large numbers and large deviations for interacting diffusions on Erd¨ os-R´ enyi graphs, Stoch. Dyn.20(2020), no. 2, 2050010, 19. MR4080158

2020
[26]

Crisanti and H

A. Crisanti and H. Sompolinsky,Dynamics of spin systems with randomly asymmetric bonds: Langevin dynamics and a spherical model, Physical Review A36(1987), no. 10, 4922

1987
[27]

arXiv preprint arXiv:2603.14573 , year=

Y. Dandi, D. Gamarnik, F. Pernice, and L. Zdeborov´ a,Rigorous asymptotics for first-order algorithms through the dynamical cavity method, arXiv preprint arXiv:2603.14573 (2026), available at2603.14573

work page arXiv 2026
[28]

Delattre, G

S. Delattre, G. Giacomin, and E. Lu¸con,A note on dynamical models on random graphs and Fokker-Planck equations, J. Stat. Phys.165(2016), no. 4, 785–798. MR3568168

2016
[29]

Dembo and R

A. Dembo and R. Gheissari,Diffusions interacting through a random matrix: universality via stochastic Taylor ex- pansion, Probab. Theory Related Fields180(2021), no. 3-4, 1057–1097. MR4288337

2021
[30]

Dembo, A

A. Dembo, A. Guionnet, and C. Mazza,Limiting dynamics for spherical models of spin glasses at high temperature, J. Stat. Phys.128(2007), no. 4, 847–881. MR2344716

2007
[31]

Dembo, E

A. Dembo, E. Lubetzky, and O. Zeitouni,Universality for Langevin-like spin glass dynamics, Ann. Appl. Probab.31 (2021), no. 6, 2864–2880. MR4350976 50 MANUEL ARNESE AND KEVIN HU

2021
[32]

Dembo and E

A. Dembo and E. Subag,Dynamics for spherical spin glasses: Gibbs distributed initial conditions, arXiv preprint arXiv:2503.23342 (2025), available at2503.23342

work page arXiv 2025
[33]

Durmus, A

A. Durmus, A. Eberle, A. Guillin, and R. Zimmer,An elementary approach to uniform in time propagation of chaos, Proc. Amer. Math. Soc.148(2020), no. 12, 5387–5398. MR4163850

2020
[34]

Eberle,Reflection couplings and contraction rates for diffusions, Probab

A. Eberle,Reflection couplings and contraction rates for diffusions, Probab. Theory Related Fields166(2016), no. 3-4, 851–886. MR3568041

2016
[35]

Eberle, A

A. Eberle, A. Guillin, and R. Zimmer,Couplings and quantitative contraction rates for Langevin dynamics, Ann. Probab.47(2019), no. 4, 1982–2010. MR3980913

2019
[36]

Z. Fan, J. Ko, B. Loureiro, Y. M Lu, and Y. Shen,Dynamical mean-field analysis of adaptive Langevin diffusions: Propagation-of-chaos and convergence of the linear response, arXiv preprint arXiv:2504.15556 (2025), available at 2504.15556

work page arXiv 2025
[37]

Z. Fan, J. Ko, B. Loureiro, Y. M. Lu, and Y. Shen,Dynamical mean-field analysis of adaptive Langevin diffusions: Replica-symmetric fixed point and empirical Bayes, arXiv preprint arXiv:2504.15558 (2025), available at2504.15558

work page arXiv 2025
[38]

Faugeras and E

O. Faugeras and E. Tanr´ e,Universality of the mean-field equations of networks of Hopfield-like neurons, J. Math. Biol.91(2025), no. 4, Paper No. 45, 51. MR4961410

2025
[39]

Gerbelot, E

C. Gerbelot, E. Troiani, F. Mignacco, F. Krzakala, and L. Zdeborov´ a,Rigorous dynamical mean-field theory for stochastic gradient descent methods, SIAM J. Math. Data Sci.6(2024), no. 2, 400–427. MR4741502

2024
[40]

M. A. Gkogkas and C. Kuehn,Graphop mean-field limits for Kuramoto-type models, SIAM J. Appl. Dyn. Syst.21 (2022), no. 1, 248–283. MR4366119

2022
[41]

Gozlan,Characterization of Talagrand’s like transportation-cost inequalities on the real line, J

N. Gozlan,Characterization of Talagrand’s like transportation-cost inequalities on the real line, J. Funct. Anal.250 (2007), no. 2, 400–425. MR2352486

2007
[42]

Grass, A

J. Grass, A. Guillin, and C. Poquet,Sharp propagation of chaos for McKean-Vlasov equation with non constant diffusion coefficient, Electron. Commun. Probab.30(2025), Paper No. 55, 12. MR4925131

2025
[43]

Grass, C

J. Grass, C. Poquet, and A. Guillin,Propagation of chaos in Fisher information, arXiv preprint arXiv:2511.20078 (2025), available at2511.20078

work page arXiv 2025
[44]

G Gripenberg, S O Londen, and O Staffans,Encyclopedia of mathematics and its applications: Volterra integral and functional equations series number 34, Cambridge University Press, Cambridge, England, 2010

2010
[45]

Guionnet,Averaged and quenched propagation of chaos for spin glass dynamics, Probab

A. Guionnet,Averaged and quenched propagation of chaos for spin glass dynamics, Probab. Theory Related Fields 109(1997), no. 2, 183–215. MR1477649

1997
[46]

Guionnet and O

A. Guionnet and O. Zeitouni,Concentration of the spectral measure for large matrices, Electron. Comm. Probab.5 (2000), 119–136. MR1781846

2000
[47]

Han,Entrywise dynamics and universality of general first order methods, Ann

Q. Han,Entrywise dynamics and universality of general first order methods, Ann. Statist.53(2025), no. 4, 1783–1807. MR4959811

2025
[48]

Hertz, G Grinstein, and S

J. Hertz, G Grinstein, and S. Solla,Irreversible spin glasses and neural networks, Heidelberg colloquium on glassy dynamics: Proceedings of a colloquium on spin glasses, optimization and neural networks held at the university of heidelberg june 9–13, 1986, 1986, pp. 538–546

1986
[49]

Hess-Childs and K

E. Hess-Childs and K. Rowan,Higher-order propagation of chaos inL 2 for interacting diffusions, Probab. Math. Phys.6(2025), no. 2, 581–646. MR4879390

2025
[50]

K. Hu, D. Lacker, and K. Ramanan,Quantitative unimodular propagation of chaos for sparse interacting diffusions, In preparation
[51]

Hu and K

K. Hu and K. Ramanan,An H-theorem for a conditional Mckean-Vlasov process related to interacting diffusions on regular trees, arXiv preprint arXiv:2412.07710 (2024), available at2412.07710

work page arXiv 2024
[52]

,A case study of the long-time behavior of the Gaussian local-field equation, arXiv preprint arXiv:2504.06449 (2025), available at2504.06449

work page arXiv 2025
[53]

Imkeller, G

P. Imkeller, G. dos Reis, and W. Salkeld,Differentiability of SDEs with drifts of super-linear growth, Electron. J. Probab.24(2019), Paper No. 3, 43. MR3916323

2019
[54]

Jabin, D

P.-E. Jabin, D. Poyato, and J. Soler,Mean-field limit of non-exchangeable systems, Comm. Pure Appl. Math.78 (2025), no. 4, 651–741. MR4863199

2025
[55]

Jabin and Z

P.-E. Jabin and Z. Wang,Mean field limit and propagation of chaos for Vlasov systems with bounded forces, J. Funct. Anal.271(2016), no. 12, 3588–3627. MR3558251

2016
[56]

,Mean field limit for stochastic particle systems, Active particles, volume 1, 2017, pp. 379–402

2017
[57]

Math.214 (2018), no

,Quantitative estimates of propagation of chaos for stochastic systems withW −1,∞ kernels, Invent. Math.214 (2018), no. 1, 523–591. MR3858403

2018
[58]

Karatzas and S

I. Karatzas and S. E. Shreve,Brownian motion and stochastic calculus, Second, Graduate Texts in Mathematics, vol. 113, Springer-Verlag, New York, 1991. MR1121940

1991
[59]

Kuehn and C

C. Kuehn and C. Xu,Vlasov equations on digraph measures, J. Differential Equations339(2022), 261–349. MR4477050

2022
[60]

Lacker,Hierarchies, entropy, and quantitative propagation of chaos for mean field diffusions, Probab

D. Lacker,Hierarchies, entropy, and quantitative propagation of chaos for mean field diffusions, Probab. Math. Phys. 4(2023), no. 2, 377–432. MR4595391 QUANTITATIVE PROPAGATION OF CHAOS AND UNIVERSALITY FOR LANGEVIN SPIN GLASS 51

2023
[61]

Lacker and L

D. Lacker and L. Le Flem,Sharp uniform-in-time propagation of chaos, Probab. Theory Related Fields187(2023), no. 1-2, 443–480. MR4634344

2023
[62]

Lacker, K

D. Lacker, K. Ramanan, and R. Wu,Local weak convergence for sparse networks of interacting processes, Ann. Appl. Probab.33(2023), no. 2, 643–688. MR4564415

2023
[63]

Theory Related Fields187(2023), no

,Marginal dynamics of interacting diffusions on unimodular Galton-Watson trees, Probab. Theory Related Fields187(2023), no. 3-4, 817–884. MR4664586

2023
[64]

Quantitative propagation of chaos for non-exchangeable diffusions via first-passage percolation

D. Lacker, L. C. Yeung, and F. Zhou,Quantitative propagation of chaos for non-exchangeable diffusions via first- passage percolation, arXiv preprint arXiv:2409.08882 (2024), available at2409.08882

work page internal anchor Pith review Pith/arXiv arXiv 2024
[65]

H. P. McKean Jr.,A class of Markov processes associated with nonlinear parabolic equations, Proc. Nat. Acad. Sci. U.S.A.56(1966), 1907–1911. MR221595

1966
[66]

Mezard and A

M. Mezard and A. Montanari,Information, physics, and computation, Oxford University Press, 2009

2009
[67]

M´ ezard, G

M. M´ ezard, G. Parisi, M. A. Virasoro, and D. J Thouless,Spin glass theory and beyond, American Institute of Physics, 1988

1988
[68]

Nualart,The Malliavin calculus and related topics, 2nd ed., Probability and Its Applications, Springer, Berlin, Germany, 2005 (en)

D. Nualart,The Malliavin calculus and related topics, 2nd ed., Probability and Its Applications, Springer, Berlin, Germany, 2005 (en)

2005
[69]

R. I. Oliveira and G. H. Reis,Interacting diffusions on random graphs with diverging average degrees: hydrodynamics and large deviations, J. Stat. Phys.176(2019), no. 5, 1057–1087. MR3999471

2019
[70]

Panchenko,The Sherrington-Kirkpatrick model, Springer Science & Business Media, 2013

D. Panchenko,The Sherrington-Kirkpatrick model, Springer Science & Business Media, 2013

2013
[71]

P. E. Protter,Stochastic integration and differential equations, Second, Applications of Mathematics (New York), vol. 21, Springer-Verlag, Berlin, 2004. Stochastic Modelling and Applied Probability. MR2020294

2004
[72]

Scheutzow,A stochastic Gronwall lemma, Infin

M. Scheutzow,A stochastic Gronwall lemma, Infin. Dimens. Anal. Quantum Probab. Relat. Top.16(2013), no. 2, 1350019, 4. MR3078830

2013
[73]

Speicher,Lectures on random matrices, EMS Series of Lectures in Mathematics, EMS Press, Berlin, [2024]©2024

R. Speicher,Lectures on random matrices, EMS Series of Lectures in Mathematics, EMS Press, Berlin, [2024]©2024. MR4779256

2024
[74]

Sznitman,Topics in propagation of chaos, Ecole d’et´ e de probabilit´ es de saint-flour xix — 1989, 1991, pp

A.-S. Sznitman,Topics in propagation of chaos, Ecole d’et´ e de probabilit´ es de saint-flour xix — 1989, 1991, pp. 165– 251

1989
[75]

Talagrand,Mean field models for spin glasses: Volume i: Basic examples, Vol

M. Talagrand,Mean field models for spin glasses: Volume i: Basic examples, Vol. 54, Springer Science & Business Media, 2010

2010
[76]

A. B. Tsybakov,Introduction to nonparametric estimation, Springer New York, 2009

2009
[77]

van Handel,Probability in high dimensions(2016)

R. van Handel,Probability in high dimensions(2016)

2016
[78]

Vershynin,High-dimensional probability, Cambridge University Press, 2018

R. Vershynin,High-dimensional probability, Cambridge University Press, 2018

2018
[79]

Villani,Topics in optimal transportation, Graduate Studies in Mathematics, American Mathematical Society, 2021

C. Villani,Topics in optimal transportation, Graduate Studies in Mathematics, American Mathematical Society, 2021

2021
[80]

Wang,Sharp local propagation of chaos for mean field particles withW −1,∞ kernels, J

S. Wang,Sharp local propagation of chaos for mean field particles withW −1,∞ kernels, J. Funct. Anal.290(2026), no. 3, Paper No. 111240, 39. MR4973611 Manuel Arnese: Department of Industrial Engineering and Operations Research, Columbia University Email address:ma4339@columbia.edu Kevin Hu: Department of Industrial Engineering and Operations Research, Col...

2026