pith. sign in

arxiv: 2510.19211 · v3 · submitted 2025-10-22 · 🧮 math.PR · math.OC

Particle system approximation of Nash equilibria in large games

Ludovic Tangpi , Nizar Touzi This is my paper

Pith reviewed 2026-05-18 05:24 UTC · model grok-4.3

classification 🧮 math.PR math.OC
keywords particle systemsNash equilibriamean field gamesMcKean-Vlasov processespropagation of chaosdisplacement monotonicityLasry-Lions monotonicity
0
0 comments X

The pith

Monotonicity of game costs ensures contractive McKean-Vlasov dynamics and uniform propagation of chaos in particle approximations to Nash equilibria.

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

The paper develops a probabilistic method to approximate Nash equilibria of symmetric games with many players by connecting them to mean field game solutions through McKean-Vlasov Langevin dynamics and their finite-particle systems. Under displacement monotonicity or Lasry-Lions monotonicity of the cost, the dynamics become contractive and the particles exhibit uniform-in-time propagation of chaos, with convergence to the mean field limit as temperature vanishes. A sympathetic reader cares because this removes the usual requirements of small interactions or special functional inequalities, giving reliable long-time approximations for large-population equilibria. The approach thereby strengthens the general theory of interacting diffusions by showing monotonicity alone suffices for the needed convergence properties.

Core claim

The authors construct a framework that approximates Nash equilibria in large symmetric N-player games through the mean field game limit, realized via McKean-Vlasov type Langevin dynamics and associated particle systems. As the temperature parameter vanishes, the particle system converges to the mean field game solution. When the cost function satisfies displacement monotonicity or Lasry-Lions monotonicity, the McKean-Vlasov process is contractive and the particle system satisfies uniform-in-time propagation of chaos. This shows that monotonicity can replace small-interaction assumptions or functional inequalities in establishing convergence for interacting diffusions.

What carries the argument

The McKean-Vlasov Langevin dynamics driven by a cost satisfying displacement or Lasry-Lions monotonicity, which enforces contractivity and thereby uniform propagation of chaos in the particle system.

If this is right

  • The particle system converges to the mean field game solution uniformly over all time horizons.
  • Nash equilibrium approximations remain valid for arbitrary time intervals when the cost is monotone.
  • Convergence of the interacting diffusions holds without assuming small interaction strength.
  • Numerical simulation of the particle system yields reliable approximations to large-game equilibria under the monotonicity condition.

Where Pith is reading between the lines

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

  • The same monotonicity might allow extension of uniform convergence results to games with common noise or to non-symmetric player interactions.
  • One could test whether the contractivity rate gives explicit error bounds between finite-N equilibria and the mean field limit.
  • The framework may apply directly to numerical solution of mean field games arising in economics or traffic models.

Load-bearing premise

The cost function must satisfy either displacement monotonicity or Lasry-Lions monotonicity.

What would settle it

A concrete example of a cost function obeying displacement monotonicity for which the associated McKean-Vlasov process fails to be contractive or the particle system fails to exhibit uniform-in-time propagation of chaos.

read the original abstract

We develop a probabilistic framework to approximate Nash equilibria in symmetric $N$-player games in the large population regime, via the analysis of associated mean field games (MFGs). The approximation is achieved through the analysis of a McKean-Vlasov type Langevin dynamics and their associated particle systems, with convergence to the MFG solution established in the limit of vanishing temperature parameter. Relying on displacement monotonicity or Lasry-Lions monotonicity of the cost function, we prove contractility of the McKean-Vlasov process and uniform-in-time propagation of chaos for the particle system. Our results contribute to the general theory of interacting diffusions by showing that monotonicity can ensure convergence without requiring small interaction assumptions or functional inequalities.

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 develops a probabilistic framework to approximate Nash equilibria in symmetric N-player games via mean-field games (MFGs). It analyzes McKean-Vlasov Langevin dynamics and associated particle systems, proving convergence to the MFG solution as the temperature parameter vanishes. Relying on displacement monotonicity or Lasry-Lions monotonicity of the cost function, the authors establish contractility of the McKean-Vlasov process and uniform-in-time propagation of chaos for the particle system. The work contributes to interacting diffusions by showing monotonicity suffices for convergence without small-interaction assumptions or functional inequalities.

Significance. If the results hold, the paper makes a solid contribution to mean-field game theory and the analysis of interacting particle systems. The uniform-in-time propagation of chaos under standard monotonicity conditions (without requiring small interactions or Poincaré inequalities) strengthens the general theory and supports long-time approximations of Nash equilibria in large games. This is particularly useful for numerical methods and applications in stochastic control and game theory.

major comments (2)
  1. [§4, Theorem 4.3] §4, Theorem 4.3 (contractivity): The contraction rate for the McKean-Vlasov flow is derived from the monotonicity constant, but the manuscript does not explicitly verify that the rate remains positive and independent of the temperature parameter in the vanishing limit; this is load-bearing for the uniform-in-time claim.
  2. [§5.1, Proposition 5.2] §5.1, Proposition 5.2 (propagation of chaos): The error bound between the particle system and the McKean-Vlasov process is stated to be uniform in time, but the dependence on N and the initial measure is not quantified with explicit constants, weakening the approximation result for finite-N Nash equilibria.
minor comments (2)
  1. [§3 and §5] The notation distinguishing the empirical measure of the particle system from the law of the McKean-Vlasov process could be made more consistent across sections 3 and 5.
  2. [Introduction] Consider adding a brief remark in the introduction on how the temperature parameter relates to the noise intensity in the Langevin dynamics.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for their positive assessment and constructive feedback, which will help clarify the key aspects of our contractivity and propagation of chaos results. We address the major comments below and will incorporate the suggested clarifications in the revised manuscript.

read point-by-point responses

  1. Referee: [§4, Theorem 4.3] §4, Theorem 4.3 (contractivity): The contraction rate for the McKean-Vlasov flow is derived from the monotonicity constant, but the manuscript does not explicitly verify that the rate remains positive and independent of the temperature parameter in the vanishing limit; this is load-bearing for the uniform-in-time claim.

    Authors: We appreciate this observation. In the proof of Theorem 4.3, the contraction rate is precisely the monotonicity constant κ > 0 of the cost function (under either displacement or Lasry-Lions monotonicity). This constant κ is independent of the temperature parameter β by construction of the assumptions on the running and terminal costs. Consequently, as β → ∞ (vanishing temperature), the rate remains κ > 0 and does not deteriorate. We will add a short remark immediately after the statement of Theorem 4.3 explicitly recording this independence and confirming that the uniform-in-time contraction holds uniformly in the vanishing-temperature limit. revision: yes

  2. Referee: [§5.1, Proposition 5.2] §5.1, Proposition 5.2 (propagation of chaos): The error bound between the particle system and the McKean-Vlasov process is stated to be uniform in time, but the dependence on N and the initial measure is not quantified with explicit constants, weakening the approximation result for finite-N Nash equilibria.

    Authors: We agree that greater explicitness would strengthen the finite-N approximation statement. The error bound in Proposition 5.2 takes the form C/√N (in the appropriate Wasserstein or total-variation distance), where the constant C depends on the second-moment bound of the initial measure, the Lipschitz constants of the drift and diffusion coefficients, and the contractivity constant κ; all of these quantities are uniform in time thanks to the McKean-Vlasov contractivity established in §4. We will revise the statement of Proposition 5.2 to display the explicit dependence of C on these quantities and add a brief paragraph in the proof explaining the moment estimates used to control C. revision: yes

Circularity Check

0 steps flagged

No significant circularity detected

full rationale

The paper's central results on contractility of the McKean-Vlasov process and uniform-in-time propagation of chaos rest on the external assumption of displacement monotonicity or Lasry-Lions monotonicity of the cost function, which are standard notions imported from the existing mean-field games literature rather than defined or fitted within this work. The derivation chain proceeds by invoking these monotonicity conditions to obtain the desired stability properties without reducing any prediction or theorem to a self-referential fit, renaming, or load-bearing self-citation. No step equates an output quantity to an input by construction, and the framework is self-contained against external benchmarks once the monotonicity hypothesis is granted.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The central claims rest on monotonicity conditions treated as domain assumptions in mean-field game theory; no free parameters or new invented entities are introduced in the abstract.

axioms (1)
  • domain assumption Cost function satisfies displacement monotonicity or Lasry-Lions monotonicity
    Invoked to prove contractility of the McKean-Vlasov process and propagation of chaos.

pith-pipeline@v0.9.0 · 5645 in / 1209 out tokens · 44345 ms · 2026-05-18T05:24:39.852216+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

67 extracted references · 67 canonical work pages

  1. [1]

    Awi, Ryan Hynd, and H

    R. Awi, Ryan Hynd, and H. Mawi. Continuous time approximation of Nash equilibria in monotone games.Commun. Contemp. Math., 26(5):2350021, 2024

    work page 2024

  2. [2]

    Springer, Cham, 2014

    Dominique Bakry, Ivan Gentil, and Michel Ledoux.Analysis and Geometry of Markov Dif- fusion Operators, volume 348 ofGrundlehren der mathematischen Wissenschaften. Springer, Cham, 2014

    work page 2014

  3. [3]

    Nash equilibrium in perturbation-stable games

    Maria-Florina Balcan and Mark Braverman. Nash equilibrium in perturbation-stable games. Theory of Computing, 13(836):1–31, 2017

    work page 2017

  4. [4]

    Billingsley.Convergence of probability measures

    P. Billingsley.Convergence of probability measures. Wiley Series in Probability and Statistics: Probability and Statistics. John Wiley & Sons Inc., New York, 2nd edition, 1999

    work page 1999

  5. [5]

    Bobkov and F

    S.G. Bobkov and F. G¨ otze. Exponential integrability and transportation cost related to loga- rithmic Sobolev inequalities.Journal of Functional Analysis, 163:1–28, 1999

    work page 1999

  6. [6]

    B¨ orgens and C. Kanzow. ADMM-type methods for generalized Nash equilibrium problems in Hilbert spaces.SIAM J. Optim., 31(377-403), 2021

    work page 2021

  7. [7]

    Cardaliaguet

    P. Cardaliaguet. Notes on mean field games (from P.-L. Lions’ lectures at Coll` ege de France). Lecture given at Tor Vergata, April–May 2010, 2010

    work page 2010

  8. [8]

    Cardaliaguet

    P. Cardaliaguet. The convergence problem in mean field games with local coupling.Applied Mathematics & Optimization, 76(1):177–215, 2017

    work page 2017

  9. [9]

    Cardaliaguet, F

    P. Cardaliaguet, F. Delarue, J.-M. Lasry, and P.-L. Lions.The master equation and the con- vergence problem in mean field games, volume 201 ofAnnals of mathematics studies. Princeton University Press, 2019

    work page 2019

  10. [10]

    Carmona and F

    R. Carmona and F. Delarue.Probabilistic theory of mean field games with applications I, volume 83 ofProbability theory and stochastic modelling. Springer International Publishing, 2018

    work page 2018

  11. [11]

    Carrillo, Robert J

    Jos´ e A. Carrillo, Robert J. McCann, and C´ edric Villani. Kinetic equilibrium rates for granular media and related equations: Entropy dissipation and mass transportation estimates.Rev. Mat. Iberoam., 19(3):971–1018, 2003

    work page 2003

  12. [12]

    Uniform-in-time propagation of chaos for kinetic mean field Langevin dynamics.Electronic Journal of Probability, 29:1–43, 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, 29:1–43, 2024. PARTICLE SYSTEMS AND LARGE STATIC GAMES 21

    work page 2024

  13. [13]

    Saddle-point dynamics: conditions for asymptotic stability of saddle points.SIAM Journal on Control and Optimization, 55(1): 486–511, 2017

    Ashish Cherukuri, Bahman Gharesifard, and Jorge Cortes. Saddle-point dynamics: conditions for asymptotic stability of saddle points.SIAM Journal on Control and Optimization, 55(1): 486–511, 2017

    work page 2017

  14. [14]

    Mean-field Langevin dynamics: Exponential convergence and annealing.Trans- actions on Machine Learning Research, 08 2022

    L´ ena¨ ıc Chizat. Mean-field Langevin dynamics: Exponential convergence and annealing.Trans- actions on Machine Learning Research, 08 2022

    work page 2022

  15. [15]

    Combettes and J.-C

    L. Combettes and J.-C. Pesquet. Stochastic quasi-Fej´ er block-coordinate fixed point iterations with random sweeping.SIAM J. Optim., 25:1221–1248, 2015

    work page 2015

  16. [16]

    Game on random environment, mean- field Langevin system, and neural networks.Math

    Giovanni Conforti, Anna Kazeykina, and Zhenjie Ren. Game on random environment, mean- field Langevin system, and neural networks.Math. Oper. Res., 48(1), 2023

    work page 2023

  17. [17]

    Interacting particle systems on sparsew-random graphs

    Carla Crucianelli and Ludovic Tangpi. Interacting particle systems on sparsew-random graphs. Preprint, 2024

    work page 2024

  18. [18]

    Non-concave games: a challenge for game theory’s next 100 years

    Constantinos Daskalakis. Non-concave games: a challenge for game theory’s next 100 years. In One Hundred Years of Game Theory: A Nobel Symposium, Econometric Society Monographs. Cambridge Univ. Press, 2026

    work page 2026

  19. [19]

    Goldberg, and Christos H

    Constantinos Daskalakis, Paul W. Goldberg, and Christos H. Papadimitriou. The complexity of computing a Nash equilibrium.38th Annual ACM Symposium on Theory of Computing (STOC), 2006

    work page 2006

  20. [20]

    Mehta, and C

    Costis Daskalakis, A. Mehta, and C. Papadimitriou. A note on approximate Nash equilibria. Theoret. Comput. Sci., 410:1581–1588, 2009

    work page 2009

  21. [21]

    Delarue, D

    F. Delarue, D. Lacker, and K. Ramanan. From the master equation to mean field game limit theory: large deviations and concentration of measure.The Annals of Probability, 48(1): 211–263, 2020

    work page 2020

  22. [22]

    Durmus, A

    A. Durmus, A. Eberle, A. Guillin, and R. Zimmer. An elementary approach to uniform in time propagation of chaos.Proceedings of the American Mathematical Society, 2020

    work page 2020

  23. [23]

    Numerical solution of Poisson partial differential equation in high dimension using two-layer neural networks.Math

    Mathias Dus and Virginie Ehrlacher. Numerical solution of Poisson partial differential equation in high dimension using two-layer neural networks.Math. Comp., 94:159–208, 2025

    work page 2025

  24. [24]

    Eberle, Z

    A. Eberle, Z. Guillin, and R. Zimmer. Quantitative Harris-type theorems for diffusions and McKean-Vlasov processes.Transactions of the American Mathematical Society, 371(10):7135– 7173, 2019

    work page 2019

  25. [25]

    Paths to constrained Nash equilibria.Applied Math

    Sjur Didrik Fl˚ am. Paths to constrained Nash equilibria.Applied Math. Optim., 27:275–289, 1993

    work page 1993

  26. [26]

    F¨ ollmer and A

    H. F¨ ollmer and A. Schied.Stochastic finance: an introduction in discrete time, volume 27 of de Gruyter studies in mathematics. de Gruyter Berlin New York, 2nd revised and extended edition, 2004

    work page 2004

  27. [27]

    Fournier and A

    N. Fournier and A. 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

  28. [28]

    Gangbo, A.R

    W. Gangbo, A.R. M´ esz´ aros, C. Mou, and J. Zhang. Mean field games master equations with non-separable Hamiltonians and displacement monotonicity.The Annals of Probability, 50(6): 2178–2217, 2022

    work page 2022

  29. [29]

    M´ esz´ aros

    Wilfrid Gangbo and A. M´ esz´ aros. Global well–posedness of master equations for deterministic displacement convex potential mean field games.Comm. Pure. Appl. Math, to appear, 2022

    work page 2022

  30. [30]

    Mean field games mas- ter equations with non-separable hamiltonians and displacement monotonicity.Ann

    Wilfrid Gangbo, Alp´ ar M´ esz´ aros, Chenchen Mou, and Jianfeng Zhang. Mean field games mas- ter equations with non-separable hamiltonians and displacement monotonicity.Ann. Probab., 50(6):2178–2217, 01 2022

    work page 2022

  31. [31]

    Mean field games master equations with non-separable Hamiltonians and displacement monotonicity.Ann

    Wilfrid Gangbo, Alpar Mezaros, Chenchen Mou, and Jianfeng Zhang. Mean field games master equations with non-separable Hamiltonians and displacement monotonicity.Ann. Probab., 50 (6):2178–2217, 2022

    work page 2022

  32. [32]

    Transport inequalities

    Nathael Gozlan and Christian L´ eonard. Transport inequalities. A survey.Markov Processes and Related Fields, 16:635–736, 2010. 22 LUDOVIC TANGPI AND NIZAR TOUZI

    work page 2010

  33. [33]

    Uniform long-time and propagation of chaos estimates for mean field kinetic particles in non-convex landscapes.J

    Arnaud Guillin and Pierre Monmarch´ e. Uniform long-time and propagation of chaos estimates for mean field kinetic particles in non-convex landscapes.J. Stat. Phys., 185(2), 2021

    work page 2021

  34. [34]

    On the approximation of Nash equilibrium points in ann-person noncooperative game.SIAM Journal on Applied Mathematics, 26(3), 1974

    Terje Hansen. On the approximation of Nash equilibrium points in ann-person noncooperative game.SIAM Journal on Applied Mathematics, 26(3), 1974

    work page 1974

  35. [35]

    GANs trained by a two time-scale update rule converge to a local Nash equilibrium.In Advances in Neural Information Processing Systems, pages 6626–6637, 2017

    Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochre- iter. GANs trained by a two time-scale update rule converge to a local Nash equilibrium.In Advances in Neural Information Processing Systems, pages 6626–6637, 2017

    work page 2017

  36. [36]

    Mean-field Langevin dynamics and energy landscape of neural networks.Ann

    Kaitong Hu, Zhenjie Ren, David Siska, and L Szpruch. Mean-field Langevin dynamics and energy landscape of neural networks.Ann. Inst. H. Poincar´ e Probab. Statist., 57(4):2043–2065, 2021

    work page 2043

  37. [37]

    Huang, R.P

    M. Huang, R.P. Malham´ e, and P.E. Caines. Large population stochastic dynamic games: closed-loop McKean–Vlasov systems and the Nash certainty equivalence principle.Communi- cations in Information & Systems, 6(3):221–252, 2006

    work page 2006

  38. [38]

    GANs and gradient flows that converge.Journal of Machine Learning Research, 24(217):1–40, 2023

    Yu-Jui Huang and Yuchong Zhang. GANs and gradient flows that converge.Journal of Machine Learning Research, 24(217):1–40, 2023

    work page 2023

  39. [39]

    C. R. Hwang. Laplace’s method revisited: weak convergence of probability measures.Ann. Probab., 8(6):1177–1182, 1980

    work page 1980

  40. [40]

    Evolution of mixed strategies in monotone games.SIAM J

    Ryan Hynd. Evolution of mixed strategies in monotone games.SIAM J. Optim., 33(4):2750– 2771, 2023

    work page 2023

  41. [41]

    Jackson and L

    J. Jackson and L. Tangpi. Quantitative convergence for displacement monotone mean field games with controlled volatility.Math. Oper. Res., 49(4):2049–2802, 2024

    work page 2049

  42. [42]

    What is local optimallity in nonconvex- nonconcave minimax optimization?Proceedings of the 37th International Conference on Ma- chine Learning, PMLR, 119:4880–4889, 2020

    Chi Jin, Praneeth Netrapalli, and Michael Jordan. What is local optimallity in nonconvex- nonconcave minimax optimization?Proceedings of the 37th International Conference on Ma- chine Learning, PMLR, 119:4880–4889, 2020

    work page 2020

  43. [43]

    Ergodicity of the underdamped mean-field Langevin dynamics.Ann

    Anna Kazeykina, Zhenjie Ren, Xiaolu Tan, and Junjian Yang. Ergodicity of the underdamped mean-field Langevin dynamics.Ann. Appl. Probab., 34(3):3181–3226, 2024

    work page 2024

  44. [44]

    Zhang, Sinho Chewi, Murat A

    Yunbum Kook, Matthew S. Zhang, Sinho Chewi, Murat A. Erdogdu, and Mufan Li. Sampling from the mean-field stationary distribution.Preprint, 2024

    work page 2024

  45. [45]

    Mean field games and interacting particle systems

    Daniel Lacker. Mean field games and interacting particle systems. Unpublished lecture notes, Columbia University, 2018

    work page 2018

  46. [46]

    Sharp uniform-in-time propagation of chaos.Probab

    Daniel Lacker and Luc Le Flem. Sharp uniform-in-time propagation of chaos.Probab. Theory Related Fields, 187:443–480, 2023

    work page 2023

  47. [47]

    Joseph P. LaSalle. Some extensions of Liapunov’s second method*.IRE Transactions on Circuit Theory, 7(4):520 – 527, 1960

    work page 1960

  48. [48]

    Lasry and P.-L

    J.-M. Lasry and P.-L. Lions. Jeux ` a champ moyen. I–Le cas stationnaire.Comptes Rendus Math´ ematique, 343(9):619–625, 2006

    work page 2006

  49. [49]

    Lasry and P.-L

    J.-M. Lasry and P.-L. Lions. Jeux ` a champ moyen. II–Horizon fini et contrˆ ole optimal.Comptes Rendus Math´ ematique, 343(10):679–684, 2006

    work page 2006

  50. [50]

    Wei Liu and Jonas M. T¨ olle. Existence and uniqueness of invariant measures for stochastic evolution equations with weakly dissipative drifts.Electronic Communications in Probability, 16:447–457, 2011

    work page 2011

  51. [51]

    Symmetries in overparametrized neural networks: A mean field view.Advances in Neural Information Processing Systems, 37, 2024

    Javier Maass and Joaquin Fontbona. Symmetries in overparametrized neural networks: A mean field view.Advances in Neural Information Processing Systems, 37, 2024

    work page 2024

  52. [52]

    Logarithm Sobolev inequalities for some nonlinear PDEs.Stochastic Processes and their Applications, 95(1):109–132, 2001

    Florent Malrieu. Logarithm Sobolev inequalities for some nonlinear PDEs.Stochastic Processes and their Applications, 95(1):109–132, 2001

    work page 2001

  53. [53]

    Ratliff, and S

    Eric Mazumdar, Lillian J. Ratliff, and S. Shankar Sastry. On gradient-based learning in continuous games.SIAM J. Math of Data Sci, 2(1), 2020

    work page 2020

  54. [54]

    M´ esz´ aros and Chenchen Mou

    Alp´ ar R. M´ esz´ aros and Chenchen Mou. Mean field games systems under displacement mono- tonicity.SIAM Journal on Mathematical Analysis, 56(1):529–553, 2024. PARTICLE SYSTEMS AND LARGE STATIC GAMES 23

    work page 2024

  55. [55]

    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

  56. [56]

    Uniform log-Sobolev inequalities for mean field particles beyond flat- convexity.Preprint, 2024

    Pierre Monmarch´ e. Uniform log-Sobolev inequalities for mean field particles beyond flat- convexity.Preprint, 2024

    work page 2024

  57. [57]

    Gradient descent GAN optimization is locally stable

    Vaishnavh Nagarajan and J Zico Kolter. Gradient descent GAN optimization is locally stable. In Advances in Neural Information Processing Systems, pages 5585–5595, 2017

    work page 2017

  58. [58]

    J. Nash. Non-cooperative games.Annals of Mathematics, 54(2):286–295, 1951

    work page 1951

  59. [59]

    Equilibrium points inn-person games.Proc

    John Nash. Equilibrium points inn-person games.Proc. Natl. Acad. Sci., USA, 36:48–49, 1950

    work page 1950

  60. [60]

    Simple search methods for finding a Nash equilibrium.Games and Economic Behavior, 63(2):642–662, 2008

    Ryan Porter, Eugene Nudelman, and Yoav Shoham. Simple search methods for finding a Nash equilibrium.Games and Economic Behavior, 63(2):642–662, 2008

    work page 2008

  61. [61]

    Global contractivity for Langevin dynamics with distribution-dependent forces and uniform in time propagation of chaos.Ann

    Katharina Schuh. Global contractivity for Langevin dynamics with distribution-dependent forces and uniform in time propagation of chaos.Ann. Inst. H. Poincar´ e Probab. Statist., 60 (2):753–789, 2024

    work page 2024

  62. [62]

    Mean-field analysis of piecewise linear solutions for wide ReLU networks.Journal of Machine Learning Research, 23 (130):1–55, 2022

    Alexander Shevchenko, Vyacheslav Kungurtsev, and Marco Mondelli. Mean-field analysis of piecewise linear solutions for wide ReLU networks.Journal of Machine Learning Research, 23 (130):1–55, 2022

    work page 2022

  63. [63]

    Villani.Optimal transport: old and new, volume 338 ofGrundlehren der mathematischen Wissenschafte

    C. Villani.Optimal transport: old and new, volume 338 ofGrundlehren der mathematischen Wissenschafte. Springer, 2009

    work page 2009

  64. [64]

    Uniform log-Sobolev inequalities for mean field particles with flat-convex energy

    Songbo Wang. Uniform log-Sobolev inequalities for mean field particles with flat-convex energy. Preprint, 2024

    work page 2024

  65. [65]

    R. W. Yeung.Information theory and network coding. Springer Science and Business Media, 2008

    work page 2008

  66. [66]

    Yi and L

    P. Yi and L. Pavel. Distributed generalized Nash equilibria computation of monotone games via double-layer preconditioned proximal-point algorithms.IEEE Trans. Control Netw. Syst., 6:299–311, 2019

    work page 2019

  67. [67]

    Existence and non-uniqueness of stationary distributions for distribution dependent SDEs.Electronic Journal of Probability, (93):1–34, 2023

    Shao-Qin Zhang. Existence and non-uniqueness of stationary distributions for distribution dependent SDEs.Electronic Journal of Probability, (93):1–34, 2023. Princeton University Email address:ludovic.tangpi@princeton.edu New York University Email address:nizar.touzi@nyu.edu

    work page 2023