pith. sign in

arxiv: 2604.14427 · v1 · submitted 2026-04-15 · 🧮 math.PR

A criterion for proving entropy chaos on path space

Luigi Borasi , Francesco Carlo De Vecchi , Stefania Ugolini This is my paper

Pith reviewed 2026-05-10 11:46 UTC · model grok-4.3

classification 🧮 math.PR
keywords entropy chaospath spacepropagation of chaosconservative diffusionsrelative entropyWiener measureinteracting particle systemstime reversal
0
0 comments X

The pith

A bound on relative entropy to the Wiener measure and weak convergence of drifts yield strong entropy chaos on path space for conservative diffusions when the limit drift is regular.

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

The paper develops a criterion for establishing strong entropy chaos at the level of entire trajectories for interacting diffusion systems in the infinite-particle limit. It works with the class of conservative diffusions, defined through time-marginal probability densities paired with current velocity fields, which remain diffusions under time reversal. Under a bound on relative entropy with respect to Wiener measure together with weak convergence of drifts and fixed-time marginal densities, the path-space entropy distance to the limit vanishes provided the limiting drift meets a regularity condition. This supplies a practical test for trajectory-level propagation of chaos in systems that may involve singular interactions.

Core claim

We prove that, given a suitable bound on the relative entropy with respect to the Wiener measure and the weak convergence of both drifts and fixed-time marginal densities, strong entropy chaos at the process level is achieved in the infinite particle limit, provided the limit drift satisfies a specific regularity condition. This stochastic framework encompasses various singular interacting particle systems and their related asymptotic scenarios.

What carries the argument

The criterion that combines a relative-entropy bound to Wiener measure with weak convergence of drifts and marginals, applied inside Carlen's class of conservative diffusions whose infinitesimal characteristic pairs are a time-marginal density and a current velocity field.

If this is right

  • Path-space entropy convergence holds rather than only fixed-time marginal convergence.
  • The same assumptions cover many singular-interaction models without needing explicit coupling constructions.
  • Time-reversal invariance of the conservative class can be used to analyze both forward and backward dynamics.
  • The criterion applies directly to a range of mean-field asymptotic regimes for particle systems.

Where Pith is reading between the lines

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

  • The regularity requirement on the limit drift may be the decisive obstacle in models with very rough interactions, suggesting that numerical checks of finite-N entropy decay could test the condition indirectly.
  • The same entropy-plus-convergence template might be adapted to other reference measures besides Wiener measure when the limiting process is non-Gaussian.
  • Because the proof exploits time-reversal, the criterion could simplify analysis of time-symmetric observables or stationary regimes in related particle systems.

Load-bearing premise

The limit drift must satisfy a specific regularity condition; if it does not, path-space entropy chaos can fail even when the entropy bound and the weak convergences hold.

What would settle it

Exhibit a sequence of interacting diffusions whose relative entropy to Wiener measure stays bounded, whose drifts and fixed-time marginal densities converge weakly, whose limit drift lacks the required regularity, and for which the path-space relative entropy to the limit process remains positive.

read the original abstract

A criterion for proving a strong form of propagation of chaos on the path space, known as entropy chaos, for a general interacting diffusion system is proposed. Our analysis focuses on the class of conservative diffusions introduced by Carlen, which are characterized by infinitesimal characteristic pairs, that is, a time-marginal probability density and a current velocity field. A key property of this broad class is that the processes remain diffusions under time-reversal. We prove that, given a suitable bound on the relative entropy (with respect to the Wiener measure) and the weak convergence of both drifts and fixed-time marginal densities, strong entropy chaos at the process level is achieved in the infinite particle limit, provided the limit drift satisfies a specific regularity condition. This stochastic framework encompasses various singular interacting particle systems and their related asymptotic scenarios.

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

2 major / 2 minor

Summary. The paper proposes a criterion for strong entropy chaos on path space for conservative diffusions (in the sense of Carlen, characterized by infinitesimal characteristic pairs consisting of time-marginal densities and current velocities). Under a relative entropy bound with respect to Wiener measure, weak convergence of drifts and fixed-time marginal densities, and an additional regularity condition on the limiting drift, the authors claim to obtain strong path-space entropy chaos in the N-particle to infinite-particle limit. The framework is asserted to cover singular interacting particle systems.

Significance. If the criterion is rigorously established and the regularity condition can be checked in concrete cases, the result would supply a practical tool for path-space propagation of chaos in a wide class of mean-field limits, extending Carlen's conservative diffusion framework. The emphasis on time-reversal invariance and entropy bounds relative to Wiener measure is a strength, as is the focus on strong (rather than weak) entropy chaos.

major comments (2)
  1. [Abstract and §1 (introduction)] The abstract and introduction assert that the criterion applies to singular interacting particle systems, yet the proof requires the limit drift to satisfy a specific regularity condition (beyond the entropy bound and weak convergences). In typical singular mean-field limits the limiting drift often lies only in L^p (p<∞) or negative Sobolev spaces; if this condition fails, the entropy-chaos conclusion does not follow. The manuscript must either verify the condition for the claimed applications or delineate precisely when it holds.
  2. [Main theorem statement and proof outline] The derivation of the path-space entropy bound from the given hypotheses (entropy control, weak convergence of drifts/marginals, and regularity) is only sketched in the abstract. The precise manner in which the regularity condition is used to pass to the limit in the relative entropy on path space needs to be spelled out, including any use of time-reversal or Girsanov-type arguments.
minor comments (2)
  1. [§2 (preliminaries)] Notation for the infinitesimal characteristic pair (density and current velocity) should be introduced with explicit reference to Carlen's original definitions to avoid ambiguity.
  2. [Theorem 1.1 or equivalent] The statement of the main criterion would benefit from a numbered theorem environment that isolates the exact hypotheses (entropy bound, weak convergences, regularity) and the conclusion (strong entropy chaos).

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the careful reading and constructive comments. The manuscript presents a sufficient criterion for strong entropy chaos on path space that explicitly includes a regularity assumption on the limiting drift. We address each major comment below.

read point-by-point responses

  1. Referee: [Abstract and §1 (introduction)] The abstract and introduction assert that the criterion applies to singular interacting particle systems, yet the proof requires the limit drift to satisfy a specific regularity condition (beyond the entropy bound and weak convergences). In typical singular mean-field limits the limiting drift often lies only in L^p (p<∞) or negative Sobolev spaces; if this condition fails, the entropy-chaos conclusion does not follow. The manuscript must either verify the condition for the claimed applications or delineate precisely when it holds.

    Authors: The criterion is sufficient rather than necessary and requires the regularity condition on the limit drift as a hypothesis. The abstract and introduction note that the framework can encompass singular systems, but only when this condition holds. We will revise the abstract and introduction to delineate the scope more precisely, stating that the result applies to singular interacting particle systems for which the limiting drift satisfies the stated regularity condition. Verification of the condition is left to specific applications, as is standard for such criteria. revision: partial

  2. Referee: [Main theorem statement and proof outline] The derivation of the path-space entropy bound from the given hypotheses (entropy control, weak convergence of drifts/marginals, and regularity) is only sketched in the abstract. The precise manner in which the regularity condition is used to pass to the limit in the relative entropy on path space needs to be spelled out, including any use of time-reversal or Girsanov-type arguments.

    Authors: The proof uses the regularity condition to obtain the necessary integrability and continuity properties that permit passing to the limit inside the relative entropy functional on path space (via, e.g., dominated convergence after suitable approximation). This step is combined with the time-reversal invariance of conservative diffusions to relate the forward and backward processes and with Girsanov-type changes of measure to control the entropy relative to Wiener measure. We will expand the proof outline and the relevant section of the revised manuscript to spell out these steps in detail. revision: yes

Circularity Check

0 steps flagged

No circularity: criterion uses external assumptions

full rationale

The paper states a sufficient condition for strong path-space entropy chaos: a relative entropy bound w.r.t. Wiener measure, weak convergence of drifts and fixed-time marginals, plus a regularity condition on the limit drift. These inputs are independent of the claimed conclusion and are not obtained by fitting or redefining the output. The analysis extends the external Carlen conservative diffusion framework without self-referential reduction, self-citation load-bearing, or smuggling an ansatz. The derivation chain therefore remains non-circular.

Axiom & Free-Parameter Ledger

0 free parameters · 2 axioms · 0 invented entities

The central claim rests on the framework of conservative diffusions and the stated convergence and entropy assumptions, without introducing new free parameters or entities.

axioms (2)
  • domain assumption The processes are conservative diffusions characterized by infinitesimal characteristic pairs (time-marginal probability density and current velocity field).
    This defines the broad class of systems to which the criterion applies, as introduced by Carlen.
  • domain assumption The processes remain diffusions under time-reversal.
    This key property is used to connect forward and backward processes in the path-space analysis.

pith-pipeline@v0.9.0 · 5431 in / 1454 out tokens · 35848 ms · 2026-05-10T11:46:42.892618+00:00 · methodology

discussion (0)

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

Reference graph

Works this paper leans on

40 extracted references · 40 canonical work pages

  1. [1]

    Albeverio, F

    S. Albeverio, F. C. De Vecchi, A. Romano, and S. Ugolini. Strong Kac’s chaos in the mean-field Bose–Einstein condensation.Stochastics and Dynamics, 20(05):2050031, 2020

    work page 2020

  2. [2]

    Albeverio, F

    S. Albeverio, F. C. De Vecchi, A. Romano, and S. Ugolini. Mean-field limit for a class of stochastic ergodic control problems.SIAM Journal on Control and Optimization, 60(1):479– 504, 2022

    work page 2022

  3. [3]

    Albeverio, F

    S. Albeverio, F. C. De Vecchi, and S. Ugolini. Entropy chaos and Bose–Einstein condensation. Journal of Statistical Physics, 168:483–507, 2017

    work page 2017

  4. [4]

    Albeverio, F

    S. Albeverio, F. C. De Vecchi, and S. Ugolini. Some connections between stochastic mechanics, optimal control, and nonlinear schr¨ odinger equations. InMathematics Going Forward: Collected Mathematical Brushstrokes, pages 505–534. Springer, 2022

    work page 2022

  5. [5]

    B. D. Anderson. Reverse-time diffusion equation models.Stochastic Processes and their Appli- cations, 12(3):313–326, 1982

    work page 1982

  6. [6]

    V. I. Bogachev, N. V. Krylov, M. R¨ ockner, and S. V. Shaposhnikov.Fokker–Planck–Kolmogorov Equations, volume 207. American Mathematical Society, 2022

    work page 2022

  7. [7]

    Borasi, F

    L. Borasi, F. C. De Vecchi, and S. Ugolini. A stochastic approach to time-dependent bose- einstein condensation.(arXiv:2506.20012), 2025

    work page arXiv 2025

  8. [8]

    Budhiraja, P

    A. Budhiraja, P. Dupuis, and M. Fischer. Large deviation properties of weakly interacting processes via weak convergence methods.Ann. Probab., 40:74–102, 01 2012

    work page 2012

  9. [9]

    E. A. Carlen. Conservative Diffusions.Communications in Mathematical Physics, 94(3):293– 315, 1984

    work page 1984

  10. [10]

    E. A. Carlen.Conservative Diffusions: A constructive approach to Nelson’s stochastic mechan- ics. Princeton University, 1984

    work page 1984

  11. [11]

    E. A. Carlen. Existence and sample path properties of the diffusions in Nelson’s stochastic mechanics. Technical report, Bielefeld TU. Bielefeld-Bochum-Stochastik, Bielefeld, 1984

    work page 1984

  12. [12]

    E. A. Carlen. Superadditivity of fisher’s information and logarithmic sobolev inequalities.Jour- nal of Functional Analysis, 101(1):194–211, 1991

    work page 1991

  13. [13]

    E. A. Carlen, M. C. Carvalho, J. Le Roux, M. Loss, and C. Villani. Entropy and chaos in the Kac model.Kinetic and Related Models, 3(1):85–122, 2010

    work page 2010

  14. [14]

    Minimization of the kullback information for some markov processes.S´ eminaire de probabilit´ es de Strasbourg, 30:288–311, 1996

    Cattiaux, Patrick, L´ eonard, and Christian. Minimization of the kullback information for some markov processes.S´ eminaire de probabilit´ es de Strasbourg, 30:288–311, 1996

    work page 1996

  15. [15]

    Cattiaux

    P. Cattiaux. Entropy on the path space and application to singular diffusions and mean-field models, 2024. 13

    work page 2024

  16. [16]

    Cattiaux, G

    P. Cattiaux, G. Conforti, I. Gentil, and C. L’eonard. Time reversal of diffusion processes under a finite entropy condition.Annales de l’Institut Henri Poincar´ e, Probabilit´ es et Statistiques, 2021

    work page 2021

  17. [17]

    Conforti and C

    G. Conforti and C. L´ eonard. Time reversal of markov processes with jumps under a finite entropy condition.Stochastic Processes and their Applications, 144:85–124, 2022

    work page 2022

  18. [18]

    D. A. Dawsont and J. G¨ artner. Large deviations from the mckean-vlasov limit for weakly interacting diffusions.Stochastics, 20(4):247–308, 1987

    work page 1987

  19. [19]

    F. C. De Vecchi and C. Rigoni. A description based on optimal transport for a class of stochastic Mckean-Vlasov control problems.arXiv preprint arXiv:2405.12960, 2024

    work page arXiv 2024

  20. [20]

    F. C. De Vecchi and S. Ugolini. An entropy approach to Bose-Einstein condensation.Commu- nications on Stochastic Analysis, 8, 12 2014

    work page 2014

  21. [21]

    Guerra and L

    F. Guerra and L. Morato. Quantization of dynamical systems and stochastic control theory. Phys. Rev. D, 27:1774–1786, 1983

    work page 1983

  22. [22]

    F¨ ollmer

    H. F¨ ollmer. Time reversal on Wiener space. In S. A. Albeverio, P. Blanchard, and L. Streit, editors,Stochastic Processes — Mathematics and Physics, pages 119–129, Berlin, Heidelberg,

    work page

  23. [23]

    Springer Berlin Heidelberg

    work page

  24. [24]

    F¨ ollmer

    H. F¨ ollmer. Random fields and diffusion processes.Ecole d’Ete de Probabilites de Saint-Flour XV-XVII, 1985-87, 1988

    work page 1985

  25. [25]

    Hauray and S

    M. Hauray and S. Mischler. On Kac’s chaos and related problems.Journal of Functional Analysis, 16(7):1423–1466, 2014

    work page 2014

  26. [26]

    U. G. Haussmann and E. Pardoux. Time reversal of diffusions.The Annals of Probability, pages 1188–1205, 1986

    work page 1986

  27. [27]

    Izydorczyk, N

    L. Izydorczyk, N. Oudjane, F. Russo, and G. Tessitore. Fokker-Planck equations with terminal condition and related McKean probabilistic representation.Nonlinear Differential Equations and Applications, volume 29(10), 2022

    work page 2022

  28. [28]

    Jabin and Z

    P.-E. Jabin and Z. Wang. Quantitative estimates of propagation of chaos for stochastic systems withw −1,∞.Inventiones mathematicae, 214(1):523–591, 2018

    work page 2018

  29. [29]

    Jordan, D

    R. Jordan, D. Kinderlehrer, and F. Otto. The variational formulation of the fokker–planck equation.SIAM Journal on Mathematical Analysis, 29(1):1–17, 1998

    work page 1998

  30. [30]

    D. Lacker. Hierarchies, entropy, and quantitative propagation of chaos for mean field diffusions. Probability and Mathematical Physics, 4(2):377–432, May 2023

    work page 2023

  31. [31]

    L´ eonard

    C. L´ eonard. A survey of the schr¨ odinger problem and some of its connections with optimal transport.Discrete and Continuous Dynamical Systems, 34(4):1533–1574, 2014

    work page 2014

  32. [32]

    Millet, D

    A. Millet, D. Nualart, and M. Sanz. Integration by parts and time reversal for diffusion processes. The Annals of Probability, pages 208–238, 1989

    work page 1989

  33. [33]

    L. M. Morato and S. Ugolini. Stochastic description of a Bose–Einstein condensate. InAnnales Henri Poincar´ e, volume 12, pages 1601–1612. Springer, 2011

    work page 2011

  34. [34]

    L. M. Morato and S. Ugolini. Localization of relative entropy in Bose–Einstein condensation of trapped interacting bosons. InSeminar on Stochastic Analysis, Random Fields and Applications VII: Centro Stefano Franscini, Ascona, May 2011, pages 197–210. Springer, 2013

    work page 2011

  35. [35]

    Nelson.Quantum Fluctuations

    E. Nelson.Quantum Fluctuations. Princeton University Press, Princeton, 1984

    work page 1984

  36. [36]

    E. Nelson. Critical diffusions. In J. Az´ ema and M. Yor, editors,S´ eminaire de Probabilit´ es XIX 1983/84, pages 1–11, Berlin, Heidelberg, 1985. Springer Berlin Heidelberg

    work page 1983

  37. [37]

    M. Pavon. Stochastic control and nonequilibrium thermodynamical systems.Applied Mathe- matics and Optimization, 19:187–202, 1989

    work page 1989

  38. [38]

    M. Pavon. Hamilton’s principle in stochastic mechanics.Journal of Mathematical Physics, 36(12):6774–6800, 1995

    work page 1995

  39. [39]

    S. Ugolini. Bose-Einstein condensation: a transition to chaos result.Communications on Stochastic Analysis, 6, 2012

    work page 2012

  40. [40]

    K. Yasue. Stochastic calculus of variations.J. Funct. Anal, 41:327–340, 1981. 14

    work page 1981