arxiv: 2605.13186 · v1 · submitted 2026-05-13 · 🧮 math.AP · math.OC· math.PR

Recognition: unknown

Nesterov acceleration for the Wasserstein minimization of displacement-convex free energies

Pierre Monmarch\'e

Authors on Pith no claims yet

Pith reviewed 2026-05-14 18:26 UTC · model grok-4.3

classification 🧮 math.AP math.OCmath.PR

keywords Nesterov accelerationWasserstein gradient flowdisplacement-convex free energyunderdamped LangevinPolyak-Łojasiewicz inequalitymean-field limitVlasov-Fokker-Planck

0 comments

The pith

The mean-field underdamped Langevin process achieves Nesterov acceleration for Wasserstein minimization of displacement-convex free energies.

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

The paper shows that the mean-field underdamped Langevin process, linked to the nonlinear Vlasov-Fokker-Planck equation, delivers accelerated convergence compared to the standard Wasserstein gradient flow when minimizing displacement-convex free energies. The improvement reaches the Nesterov rate, scaling as the square root of the Polyak-Łojasiewicz constant of the energy, which is optimal for the gradient flow itself. This extension from the linear case to the nonlinear mean-field setting rests on a recent breakthrough that carries over without major new obstructions. A reader would care because the result points to faster equilibration in high-dimensional sampling and optimization problems governed by these energies.

Core claim

The mean-field underdamped Langevin process achieves a Nesterov acceleration with respect to the Wasserstein gradient flow of a displacement-convex free energy, in the sense that it converges at a rate of order given by the square-root of the Polyak-Łojasiewicz constant of the free energy.

What carries the argument

The mean-field underdamped Langevin process (or its associated nonlinear Vlasov-Fokker-Planck equation), which realizes the diffusive-to-ballistic improvement in entropy decay.

If this is right

Convergence rates for Wasserstein minimization of such energies improve from order linear in the PL constant to order square-root.
The acceleration applies directly in the nonlinear mean-field regime once the linear result is available.
Particle systems whose empirical measures evolve under these dynamics equilibrate faster than under plain gradient flow.
Sampling and optimization algorithms based on the underdamped Langevin dynamics gain a theoretical speed-up guarantee for this class of energies.

Where Pith is reading between the lines

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

The same acceleration mechanism might extend to other mean-field limits where a PL inequality holds locally, such as certain McKean-Vlasov equations with interaction potentials.
Numerical tests on granular-media or aggregation-diffusion energies could verify the predicted square-root scaling in practice.
If the PL constant can be estimated or bounded a priori, these dynamics would supply a parameter-free way to tune accelerated sampling schemes.

Load-bearing premise

The free energy must be displacement-convex and satisfy a Polyak-Łojasiewicz inequality, with the nonlinear extension relying on the linear-case breakthrough carrying over without additional obstructions.

What would settle it

A numerical simulation of the mean-field underdamped Langevin process for a concrete displacement-convex free energy obeying a Polyak-Łojasiewicz inequality, checking whether the measured convergence rate scales as the square root rather than linearly with the constant.

read the original abstract

We show that the mean-field underdamped Langevin process (associated to the non-linear Vlasov-Fokker-Planck equation) achieves a Nesterov acceleration with respect to the Wasserstein gradient flow of a displacement-convex free energy, in the sense that it converges at a rate of order given by the square-root of the Polyak-{\L}ojasiewicz constant of the free energy (which is the optimal convergence rate for the corresponding gradient flow). This result has been made possible by the recent breakthrough [42] by Jianfeng Lu, which establishes such a \emph{diffusive-to-ballistic} improvement in term of entropy in the linear case.

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

Extends Lu's linear diffusive-to-ballistic improvement to nonlinear displacement-convex free energies, but the carry-over of the key estimates needs explicit verification for the mean-field drift.

read the letter

The main point is that this paper shows the mean-field underdamped Langevin dynamics achieves the accelerated sqrt(mu) convergence rate for Wasserstein minimization of displacement-convex free energies that also satisfy a Polyak-Łojasiewicz inequality. It takes the linear-case breakthrough from Lu and applies it to the nonlinear Vlasov-Fokker-Planck setting, keeping the optimal rate relative to the plain Wasserstein gradient flow.

Referee Report

1 major / 2 minor

Summary. The manuscript claims that the mean-field underdamped Langevin process (nonlinear Vlasov-Fokker-Planck equation) achieves Nesterov acceleration relative to the Wasserstein gradient flow of a displacement-convex free energy satisfying a Polyak-Łojasiewicz inequality, yielding convergence at rate O(sqrt(mu)) where mu is the PL constant. This is presented as an extension of the linear-case diffusive-to-ballistic improvement established in reference [42].

Significance. If the nonlinear extension is rigorously justified, the result would be significant for accelerated optimization in Wasserstein space, as it extends the optimal rate from the linear setting to mean-field systems with interaction potentials while preserving the displacement-convexity and PL assumptions. The work correctly credits [42] and identifies the key structural assumptions needed for the rate.

major comments (1)

[Proof of main theorem (extension from [42])] The central extension from the linear case in [42] to the nonlinear VFP equation is load-bearing for the main claim but lacks explicit justification. In the proof of the main theorem (likely §3 or the analysis following the statement of Theorem 1.1), the additional mean-field drift term arising from the nonlinear interaction potential must be controlled in the entropy dissipation or Lyapunov functional; simply invoking [42] by reference does not automatically close the differential inequality when the potential is non-quadratic, as the linear estimates may fail to carry over without additional bounds on the transport term.

minor comments (2)

[Abstract] The abstract and introduction could more explicitly state the precise form of the rate (e.g., whether it is asymptotic or includes constants) and the precise class of free energies considered beyond displacement-convexity and PL.
[Introduction and preliminaries] Notation for the Wasserstein gradient flow and the underdamped process should be unified across sections to avoid minor confusion between the linear and nonlinear settings.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the positive evaluation of the significance of the result and for identifying the need for more explicit justification of the nonlinear extension. We address the major comment below and will revise the manuscript to strengthen the proof.

read point-by-point responses

Referee: The central extension from the linear case in [42] to the nonlinear VFP equation is load-bearing for the main claim but lacks explicit justification. In the proof of the main theorem (likely §3 or the analysis following the statement of Theorem 1.1), the additional mean-field drift term arising from the nonlinear interaction potential must be controlled in the entropy dissipation or Lyapunov functional; simply invoking [42] by reference does not automatically close the differential inequality when the potential is non-quadratic, as the linear estimates may fail to carry over without additional bounds on the transport term.

Authors: We agree that the current draft does not make the control of the nonlinear mean-field drift sufficiently explicit. In the revised version we will add a dedicated intermediate result (new Lemma 3.3) that bounds the contribution of the interaction term to the time derivative of the Lyapunov functional. The bound follows from displacement convexity of the free energy together with the PL inequality and the fact that the mean-field drift is the Wasserstein gradient of the interaction energy; this yields an estimate of the same form as the linear case, allowing the differential inequality to close with the same constants. The proof of Theorem 1.1 will be expanded to include these steps rather than citing [42] directly. revision: yes

Circularity Check

0 steps flagged

No circularity: result extends independent linear-case breakthrough

full rationale

The paper's derivation chain invokes the linear-case diffusive-to-ballistic improvement from the external reference [42] by Jianfeng Lu (distinct author) and adapts it to the nonlinear Vlasov-Fokker-Planck setting under displacement-convexity plus Polyak-Łojasiewicz assumptions. No quoted step defines a quantity in terms of itself, renames a fitted input as a prediction, or reduces the central rate claim to a self-citation chain; the extension is presented as carrying over without additional obstructions, but the load-bearing estimates originate outside the present manuscript. The derivation is therefore self-contained against external benchmarks.

Axiom & Free-Parameter Ledger

0 free parameters · 2 axioms · 0 invented entities

The claim rests on standard domain assumptions from optimal transport and convex analysis with no new free parameters or invented entities.

axioms (2)

domain assumption The free energy functional is displacement-convex.
Explicitly required for the Wasserstein gradient flow setting.
domain assumption The free energy satisfies a Polyak-Łojasiewicz inequality.
Used to obtain the stated convergence rate.

pith-pipeline@v0.9.0 · 5407 in / 1244 out tokens · 45672 ms · 2026-05-14T18:26:29.144885+00:00 · methodology

discussion (0)

Reference graph

Works this paper leans on

67 extracted references · 67 canonical work pages · 3 internal anchors

[1]

Vari- ational methods for the kinetic fokker–planck equation.Analysis & PDE, 17(6):1953– 2010, 2024

Dallas Albritton, Scott Armstrong, Jean-Christophe Mourrat, and Matthew Novack. Vari- ational methods for the kinetic fokker–planck equation.Analysis & PDE, 17(6):1953– 2010, 2024

work page 1953
[2]

Shifted composition iv: toward ballistic acceleration for log-concave sampling.arXiv preprint arXiv:2506.23062, 2025

Jason M Altschuler, Sinho Chewi, and Matthew S Zhang. Shifted composition iv: toward ballistic acceleration for log-concave sampling.arXiv preprint arXiv:2506.23062, 2025

work page arXiv 2025
[3]

Springer Science & Business Media, 2005

Luigi Ambrosio, Nicola Gigli, and Giuseppe Savar´ e.Gradient flows: in metric spaces and in the space of probability measures. Springer Science & Business Media, 2005

work page 2005
[4]

Hypocoercivity of piecewise deterministic markov process-monte carlo.The Annals of Applied Probability, 31(5):2478–2517, 2021

Christophe Andrieu, Alain Durmus, Nikolas N¨ usken, and Julien Roussel. Hypocoercivity of piecewise deterministic markov process-monte carlo.The Annals of Applied Probability, 31(5):2478–2517, 2021. 17

work page 2021
[5]

Maximum mean discrep- ancy gradient flow.Advances in neural information processing systems, 32, 2019

Michael Arbel, Anna Korba, Adil Salim, and Arthur Gretton. Maximum mean discrep- ancy gradient flow.Advances in neural information processing systems, 32, 2019

work page 2019
[6]

Springer, Cham, 2014

Dominique Bakry, Ivan Gentil, and Michel Ledoux.Analysis and geometry of Markov dif- fusion operators, volume 348 ofGrundlehren der Mathematischen Wissenschaften [Fun- damental Principles of Mathematical Sciences]. Springer, Cham, 2014

work page 2014
[7]

Gradient flow approach to local mean-field spin systems

Kaveh Bashiri and Anton Bovier. Gradient flow approach to local mean-field spin systems. Stochastic Processes and their Applications, 130(3):1461–1514, 2020

work page 2020
[8]

Bakry–´ emery meet villani.Journal of functional analysis, 273(7):2275– 2291, 2017

Fabrice Baudoin. Bakry–´ emery meet villani.Journal of functional analysis, 273(7):2275– 2291, 2017

work page 2017
[9]

A criterion on the free energy for log-Sobolev inequalities in mean-field particle systems.arXiv e-prints, page arXiv:2503.24372, March 2025

Roland Bauerschmidt, Thierry Bodineau, and Benoˆ ıt Dagallier. A criterion on the free energy for log-Sobolev inequalities in mean-field particle systems.arXiv e-prints, page arXiv:2503.24372, March 2025

work page arXiv 2025
[10]

A piecewise deterministic scaling limit of lifted Metropolis-Hastings in the Curie-Weiss model.Ann

Joris Bierkens and Gareth Roberts. A piecewise deterministic scaling limit of lifted Metropolis-Hastings in the Curie-Weiss model.Ann. Appl. Probab., 27(2):846–882, 2017

work page 2017
[11]

Quantitative stability of constant equilibria in a non-linear alignment model of self-propelled particles

´Emeric Bouin and Amic Frouvelle. Quantitative stability of constant equilibria in a non- linear alignment model of self-propelled particles.arXiv preprint arXiv:2604.05927, 2026

work page internal anchor Pith review Pith/arXiv arXiv 2026
[12]

Hypocoercivity meets lifts.Kinetic and Related Models, 20(0):34–55, 2026

Giovanni Brigati, Francis L¨ orler, and Lihan Wang. Hypocoercivity meets lifts.Kinetic and Related Models, 20(0):34–55, 2026

work page 2026
[13]

Proximal optimal transport modeling of population dynamics

Charlotte Bunne, Laetitia Papaxanthos, Andreas Krause, and Marco Cuturi. Proximal optimal transport modeling of population dynamics. InInternational Conference on Artificial Intelligence and Statistics, pages 6511–6528. PMLR, 2022

work page 2022
[14]

On explicit l 2-convergence rate estimate for un- derdamped langevin dynamics.Archive for Rational Mechanics and Analysis, 247(5):90, 2023

Yu Cao, Jianfeng Lu, and Lihan Wang. On explicit l 2-convergence rate estimate for un- derdamped langevin dynamics.Archive for Rational Mechanics and Analysis, 247(5):90, 2023

work page 2023
[15]

Springer, 2018

Ren´ e Carmona, Fran¸ cois Delarue, et al.Probabilistic theory of mean field games with applications I-II, volume 3. Springer, 2018

work page 2018
[16]

Carrillo, Robert J

Jos´ e A. Carrillo, Robert J. McCann, and C´ edric Villani. Kinetic equilibration rates for granular media and related equations: entropy dissipation and mass transportation estimates.Revista Matem´ atica Iberoamericana, 19(3):971 – 1018, 2003

work page 2003
[17]

Entropic multipliers method for langevin diffusion and weighted log sobolev inequalities.Journal of Functional Analysis, 277(11):108288, 2019

Patrick Cattiaux, Arnaud Guillin, Pierre Monmarch´ e, and Chaoen Zhang. Entropic multipliers method for langevin diffusion and weighted log sobolev inequalities.Journal of Functional Analysis, 277(11):108288, 2019

work page 2019
[18]

Uniform-in-time propagation of chaos for kinetic mean field Langevin dynamics.Electronic Journal of Probability, 29(none):1 – 43, 2024

Fan Chen, Yiqing Lin, Zhenjie Ren, and Songbo Wang. Uniform-in-time propagation of chaos for kinetic mean field Langevin dynamics.Electronic Journal of Probability, 29(none):1 – 43, 2024

work page 2024
[19]

Uniform-in-time propagation of chaos for mean field langevin dynamics.arXiv preprint arXiv:2212.03050, 2022

Fan Chen, Zhenjie Ren, and Songbo Wang. Uniform-in-time propagation of chaos for mean field langevin dynamics.arXiv preprint arXiv:2212.03050, 2022

work page arXiv 2022
[20]

Mean-field langevin dynamics : Exponential convergence and annealing

L´ ena¨ ıc Chizat. Mean-field langevin dynamics : Exponential convergence and annealing. Transactions on Machine Learning Research, 2022. 18

work page 2022
[21]

Dalalyan and Lionel Riou-Durand

Arnak S. Dalalyan and Lionel Riou-Durand. On sampling from a log-concave density using kinetic Langevin diffusions.Bernoulli, 26(3):1956 – 1988, 2020

work page 1956
[22]

Mat´ ıas G Delgadino, Rishabh S Gvalani, Grigorios A Pavliotis, and Scott A Smith. Phase transitions, logarithmic sobolev inequalities, and uniform-in-time propagation of chaos for weakly interacting diffusions.Communications in Mathematical Physics, pages 1–49, 2023

work page 2023
[23]

Randomized Hamiltonian Monte Carlo as scaling limit of the bouncy particle sampler and dimension-free convergence rates.The Annals of Applied Probability, 31(6):2612 – 2662, 2021

George Deligiannidis, Daniel Paulin, Alexandre Bouchard-Cˆ ot´ e, and Arnaud Doucet. Randomized Hamiltonian Monte Carlo as scaling limit of the bouncy particle sampler and dimension-free convergence rates.The Annals of Applied Probability, 31(6):2612 – 2662, 2021

work page 2021
[24]

Analysis of a nonreversible markov chain sampler.Annals of Applied Probability, pages 726–752, 2000

Persi Diaconis, Susan Holmes, and Radford M Neal. Analysis of a nonreversible markov chain sampler.Annals of Applied Probability, pages 726–752, 2000

work page 2000
[25]

Hypocoercivity for linear kinetic equations conserving mass.Transactions of the American Mathematical Society, 367(6):3807–3828, 2015

Jean Dolbeault, Cl´ ement Mouhot, and Christian Schmeiser. Hypocoercivity for linear kinetic equations conserving mass.Transactions of the American Mathematical Society, 367(6):3807–3828, 2015

work page 2015
[26]

Asymptotic bias of inexact markov chain monte carlo methods in high dimension.The Annals of Applied Probability, 34(4):3435–3468, 2024

Alain Durmus and Andreas Eberle. Asymptotic bias of inexact markov chain monte carlo methods in high dimension.The Annals of Applied Probability, 34(4):3435–3468, 2024

work page 2024
[27]

Non-reversible lifts of reversible diffusion processes and relaxation times

L¨ orler Francis Eberle, Andreas. Non-reversible lifts of reversible diffusion processes and relaxation times

work page
[28]

Continuized accelerations of deterministic and stochastic gradient descents, and of gossip algorithms.Advances in Neural Information Processing Systems, 34:28054–28066, 2021

Mathieu Even, Rapha¨ el Berthier, Francis Bach, Nicolas Flammarion, Hadrien Hendrikx, Pierre Gaillard, Laurent Massouli´ e, and Adrien Taylor. Continuized accelerations of deterministic and stochastic gradient descents, and of gossip algorithms.Advances in Neural Information Processing Systems, 34:28054–28066, 2021

work page 2021
[29]

Sharp hypocoercive convergence estimates for underdamped Langevin dynamics via the modified $L^2$ method

Zexi Fan, Bowen Li, and Jianfeng Lu. Sharp hypocoercive convergence estimates for underdamped Langevin dynamics via the modifiedL 2 method.arXiv preprint arXiv:2604.10068, 2026

work page internal anchor Pith review Pith/arXiv arXiv 2026
[30]

On the rate of convergence in wasserstein distance of the empirical measure.Probability theory and related fields, 162(3-4):707–738, 2015

Nicolas Fournier and Arnaud Guillin. On the rate of convergence in wasserstein distance of the empirical measure.Probability theory and related fields, 162(3-4):707–738, 2015

work page 2015
[31]

Spectral decompositions andL 2-operator norms of toy hypocoercive semi-groups.Kinetic and related models, 6(2):317–372, 2013

S´ ebastien Gadat and Laurent Miclo. Spectral decompositions andL 2-operator norms of toy hypocoercive semi-groups.Kinetic and related models, 6(2):317–372, 2013

work page 2013
[32]

A math- ematical perspective on transformers.Bulletin of the American Mathematical Society, 62(3):427–479, 2025

Borjan Geshkovski, Cyril Letrouit, Yury Polyanskiy, and Philippe Rigollet. A math- ematical perspective on transformers.Bulletin of the American Mathematical Society, 62(3):427–479, 2025

work page 2025
[33]

HMC and Underdamped Langevin United in the Unadjusted Convex Smooth Case.SIAM/ASA Journal on Uncertainty Quantification, 13(1):278–303, 2025

Nicolas Gouraud, Pierre Le Bris, Adrien Majka, and Pierre Monmarch´ e. HMC and Underdamped Langevin United in the Unadjusted Convex Smooth Case.SIAM/ASA Journal on Uncertainty Quantification, 13(1):278–303, 2025

work page 2025
[34]

Uniform Poincar´ e and log- arithmic Sobolev inequalities for mean field particle systems.The Annals of Applied Probability, 32(3):1590 – 1614, 2022

Arnaud Guillin, Wei Liu, Liming Wu, and Chaoen Zhang. Uniform Poincar´ e and log- arithmic Sobolev inequalities for mean field particle systems.The Annals of Applied Probability, 32(3):1590 – 1614, 2022. 19

work page 2022
[35]

Uniform long-time and propagation of chaos estimates for mean field kinetic particles in non-convex landscapes.Journal of Statistical Physics, 185:1–20, 2021

Arnaud Guillin and Pierre Monmarch´ e. Uniform long-time and propagation of chaos estimates for mean field kinetic particles in non-convex landscapes.Journal of Statistical Physics, 185:1–20, 2021

work page 2021
[36]

Short and long time behavior of the fokker–planck equation in a confining potential and applications.Journal of Functional Analysis, 244(1):95–118, 2007

Fr´ ed´ eric H´ erau. Short and long time behavior of the fokker–planck equation in a confining potential and applications.Journal of Functional Analysis, 244(1):95–118, 2007

work page 2007
[37]

Isotropic hypoellipticity and trend to equilibrium for the fokker-planck equation with a high-degree potential.Archive for Rational Mechanics and Analysis, 171(2):151–218, 2004

Fr´ ed´ eric H´ erau and Francis Nier. Isotropic hypoellipticity and trend to equilibrium for the fokker-planck equation with a high-degree potential.Archive for Rational Mechanics and Analysis, 171(2):151–218, 2004

work page 2004
[38]

Mean-field Langevin dy- namics and energy landscape of neural networks.Annales de l’Institut Henri Poincar´ e, Probabilit´ es et Statistiques, 57(4):2043 – 2065, 2021

Kaitong Hu, Zhenjie Ren, David ˇSiˇ ska, and Lukasz Szpruch. Mean-field Langevin dy- namics and energy landscape of neural networks.Annales de l’Institut Henri Poincar´ e, Probabilit´ es et Statistiques, 57(4):2043 – 2065, 2021

work page 2043
[39]

Variational inference via wasserstein gradient flows.Advances in Neural Information Processing Systems, 35:14434–14447, 2022

Marc Lambert, Sinho Chewi, Francis Bach, Silv` ere Bonnabel, and Philippe Rigollet. Variational inference via wasserstein gradient flows.Advances in Neural Information Processing Systems, 35:14434–14447, 2022

work page 2022
[40]

Convergence rates for an adap- tive biasing potential scheme from a wasserstein optimization perspective.Nonlinearity, 39(4):045016, 2026

Tony Leli` evre, Xuyang Lin, and Pierre Monmarch´ e. Convergence rates for an adap- tive biasing potential scheme from a wasserstein optimization perspective.Nonlinearity, 39(4):045016, 2026

work page 2026
[41]

Ensembles semi-analytiques.IHES notes, page 220, 1965

Stanislaw Lojasiewicz. Ensembles semi-analytiques.IHES notes, page 220, 1965

work page 1965
[42]

A sharp hypocoercive entropy decay estimate for underdamped Langevin dynamics

Jianfeng Lu. A sharp hypocoercive entropy decay estimate for underdamped Langevin dynamics.arXiv e-prints, page arXiv:2605.01933, May 2026

work page internal anchor Pith review Pith/arXiv arXiv 2026
[43]

On explicit l 2-convergence rate estimate for piecewise deterministic markov processes in mcmc algorithms.The Annals of Applied Probability, 32(2):1333–1361, 2022

Jianfeng Lu and Lihan Wang. On explicit l 2-convergence rate estimate for piecewise deterministic markov processes in mcmc algorithms.The Annals of Applied Probability, 32(2):1333–1361, 2022

work page 2022
[44]

A mean field view of the land- scape of two-layer neural networks.Proceedings of the National Academy of Sciences, 115(33):E7665–E7671, 2018

Song Mei, Andrea Montanari, and Phan-Minh Nguyen. A mean field view of the land- scape of two-layer neural networks.Proceedings of the National Academy of Sciences, 115(33):E7665–E7671, 2018

work page 2018
[45]

On the implicit regularization of langevin dynamics with projected noise.arXiv preprint arXiv:2602.12257, 2026

Govind Menon, Austin J Stromme, and Adrien Vacher. On the implicit regularization of langevin dynamics with projected noise.arXiv preprint arXiv:2602.12257, 2026

work page arXiv 2026
[46]

´Etude spectrale minutieuse de processus moins ind´ ecis que les autres

Laurent Miclo and Pierre Monmarch´ e. ´Etude spectrale minutieuse de processus moins ind´ ecis que les autres. InS´ eminaire de Probabilit´ es XLV, volume 2078 ofLecture Notes in Math., pages 459–481. Springer, Cham, 2013

work page 2078
[47]

Piecewise deterministic simulated annealing.ALEA Lat

Pierre Monmarch´ e. Piecewise deterministic simulated annealing.ALEA Lat. Am. J. Probab. Math. Stat., 13(1):357–398, 2016

work page 2016
[48]

Generalized Γ calculus and application to interacting particles on a graph.Potential Analysis, 50:439–466, 2019

Pierre Monmarch´ e. Generalized Γ calculus and application to interacting particles on a graph.Potential Analysis, 50:439–466, 2019

work page 2019
[49]

An entropic approach for Hamiltonian Monte Carlo: The idealized case.The Annals of Applied Probability, 34(2):2243 – 2293, 2024

Pierre Monmarch´ e. An entropic approach for Hamiltonian Monte Carlo: The idealized case.The Annals of Applied Probability, 34(2):2243 – 2293, 2024

work page 2024
[50]

Free energy Wasserstein gradient flow and their particle counter- parts: toy model, (degenerate) PL inequalities and exit times.arXiv e-prints, page arXiv:2510.16506, October 2025

Pierre Monmarch´ e. Free energy Wasserstein gradient flow and their particle counter- parts: toy model, (degenerate) PL inequalities and exit times.arXiv e-prints, page arXiv:2510.16506, October 2025. 20

work page arXiv 2025
[51]

Uniform log-sobolev inequalities for mean field particles beyond flat- convexity.Stochastic Processes and their Applications, 2025

Pierre Monmarch´ e. Uniform log-sobolev inequalities for mean field particles beyond flat- convexity.Stochastic Processes and their Applications, 2025

work page 2025
[52]

Local convergence rates for wasserstein gradient flows and mckean-vlasov equations with multiple stationary solutions.Probability Theory and Related Fields, pages 1–59, 2025

Pierre Monmarch´ e and Julien Reygner. Local convergence rates for wasserstein gradient flows and mckean-vlasov equations with multiple stationary solutions.Probability Theory and Related Fields, pages 1–59, 2025

work page 2025
[53]

Exact targeting of gibbs distributions using velocity-jump processes.Stochastics and Partial Differential Equa- tions: Analysis and Computations, pages 1–40, 2022

Pierre Monmarch´ e, Matthias Rousset, and Pierre-Andr´ e Zitt. Exact targeting of gibbs distributions using velocity-jump processes.Stochastics and Partial Differential Equa- tions: Analysis and Computations, pages 1–40, 2022

work page 2022
[54]

Long-time behaviour and propagation of chaos for mean field kinetic particles.Stochastic Processes and their Applications, 127(6):1721–1737, 2017

Pierre Monmarch´ e. Long-time behaviour and propagation of chaos for mean field kinetic particles.Stochastic Processes and their Applications, 127(6):1721–1737, 2017

work page 2017
[55]

A method for solving the convex programming problem with convergence rate o (1/k2)

Yurii Nesterov. A method for solving the convex programming problem with convergence rate o (1/k2). InDokl akad nauk Sssr, volume 269, page 543, 1983

work page 1983
[56]

The geometry of dissipative evolution equations: the porous medium equation

Felix Otto. The geometry of dissipative evolution equations: the porous medium equation. 2001

work page 2001
[57]

E. A. J. F. Peters and G. de With. Rejection-free monte carlo sampling for general potentials.Phys. Rev. E 85, 026703, 2012

work page 2012
[58]

Entropic approximation of wasserstein gradient flows.SIAM Journal on Imaging Sciences, 8(4):2323–2351, 2015

Gabriel Peyr´ e. Entropic approximation of wasserstein gradient flows.SIAM Journal on Imaging Sciences, 8(4):2323–2351, 2015

work page 2015
[59]

Some methods of speeding up the convergence of iteration methods.Ussr computational mathematics and mathematical physics, 4(5):1–17, 1964

Boris T Polyak. Some methods of speeding up the convergence of iteration methods.Ussr computational mathematics and mathematical physics, 4(5):1–17, 1964

work page 1964
[60]

Etienne Sandier and Sylvia Serfaty. Gamma-convergence of gradient flows with applica- tions to ginzburg-landau.Communications on Pure and Applied Mathematics: A Journal Issued by the Courant Institute of Mathematical Sciences, 57(12):1627–1672, 2004

work page 2004
[61]

Understanding the accelera- tion phenomenon via high-resolution differential equations.Mathematical Programming, 195(1):79–148, 2022

Bin Shi, Simon S Du, Michael I Jordan, and Weijie J Su. Understanding the accelera- tion phenomenon via high-resolution differential equations.Mathematical Programming, 195(1):79–148, 2022

work page 2022
[62]

A differential equation for model- ing nesterov’s accelerated gradient method: Theory and insights.Journal of Machine Learning Research, 17(153):1–43, 2016

Weijie Su, Stephen Boyd, and Emmanuel J Candes. A differential equation for model- ing nesterov’s accelerated gradient method: Theory and insights.Journal of Machine Learning Research, 17(153):1–43, 2016

work page 2016
[63]

Quantitative propagation of chaos of mckean-vlasov equations via the master equation

Alvin Tsz Ho Tse. Quantitative propagation of chaos of mckean-vlasov equations via the master equation. 2019

work page 2019
[64]

Hypocoercivity.Mem

C´ edric Villani. Hypocoercivity.Mem. Amer. Math. Soc., 202(950):iv+141, 2009

work page 2009
[65]

Uniform log-Sobolev inequalities for mean field particles with flat-convex energy.arXiv e-prints, page arXiv:2408.03283, August 2024

Songbo Wang. Uniform log-Sobolev inequalities for mean field particles with flat-convex energy.arXiv e-prints, page arXiv:2408.03283, August 2024

work page arXiv 2024
[66]

Large-scale concentration and relaxation for mean-field langevin particle systems.arXiv preprint arXiv:2508.16428, 2025

Songbo Wang. Large-scale concentration and relaxation for mean-field langevin particle systems.arXiv preprint arXiv:2508.16428, 2025

work page arXiv 2025
[67]

A lyapunov analysis of accelerated methods in optimization.Journal of Machine Learning Research, 22(113):1–34, 2021

Ashia C Wilson, Ben Recht, and Michael I Jordan. A lyapunov analysis of accelerated methods in optimization.Journal of Machine Learning Research, 22(113):1–34, 2021. 21

work page 2021