×

Sharp uniform-in-time propagation of chaos. (English) Zbl 07735855

Summary: We prove the optimal rate of quantitative propagation of chaos, uniformly in time, for interacting diffusions. Our main examples are interactions governed by convex potentials and models on the torus with small interactions. We show that the distance between the \(k\)-particle marginal of the \(n\)-particle system and its limiting product measure is \(O((k/n)^2)\), uniformly in time, with distance measured either by relative entropy, squared quadratic Wasserstein metric, or squared total variation. Our proof is based on an analysis of relative entropy through the BBGKY hierarchy, adapting prior work of the first author to the time-uniform case by means of log-Sobolev inequalities.

MSC:

82C22 Interacting particle systems in time-dependent statistical mechanics
60H10 Stochastic ordinary differential equations (aspects of stochastic analysis)

References:

[1] Acebrón, JA; Bonilla, LL; Vicente, CJP; Ritort, F.; Spigler, R., The Kuramoto model: a simple paradigm for synchronization phenomena, Rev. Mod. Phys., 77, 1, 137 (2005) · doi:10.1103/RevModPhys.77.137
[2] Arnaudon, M.; Del Moral, P., A second order analysis of McKean-Vlasov semigroups, Ann. Appl. Probab., 30, 6, 2613-2664 (2020) · Zbl 1504.60136 · doi:10.1214/20-AAP1568
[3] Bakry, D.; Gentil, I.; Ledoux, M., Analysis and Geometry of Markov Diffusion Operators (2014), Berlin: Springer, Berlin · Zbl 1376.60002 · doi:10.1007/978-3-319-00227-9
[4] Bertini, L.; Giacomin, G.; Pakdaman, K., Dynamical aspects of mean field plane rotators and the Kuramoto model, J. Stat. Phys., 138, 1, 270-290 (2010) · Zbl 1187.82067 · doi:10.1007/s10955-009-9908-9
[5] Bogachev, VI; Krylov, NV; Röckner, M.; Shaposhnikov, SV, Fokker-Planck-Kolmogorov Equations (2015), Amsterdam: American Mathematical Society, Amsterdam · Zbl 1342.35002
[6] Bogachev, VI; Röckner, M.; Shaposhnikov, SV, Distances between transition probabilities of diffusions and applications to nonlinear Fokker-Planck-Kolmogorov equations, J. Funct. Anal., 271, 5, 1262-1300 (2016) · Zbl 1345.35051 · doi:10.1016/j.jfa.2016.05.016
[7] Bresch, D., Jabin, P.-E., Soler, J.: A new approach to the mean-field limit of Vlasov-Fokker-Planck equations, arXiv preprint arXiv:2203.15747 (2022)
[8] Bresch, D., Jabin, P.-E., Wang, Z.: Mean-field limit and quantitative estimates with singular attractive kernels, arXiv preprint arXiv:2011.08022 (2020)
[9] Brunick, B.; Shreve, S., Mimicking an Itô process by a solution of a stochastic differential equation, Ann. Appl. Probab., 23, 4, 1584-1628 (2013) · Zbl 1284.60109 · doi:10.1214/12-AAP881
[10] Carrillo, JA; Gvalani, RS; Pavliotis, GA; Schlichting, A., Long-time behaviour and phase transitions for the McKean-Vlasov equation on the torus, Arch. Ration. Mech. Anal., 235, 1, 635-690 (2020) · Zbl 1436.58025 · doi:10.1007/s00205-019-01430-4
[11] Cattiaux, P.; Guillin, A.; Malrieu, F., Probabilistic approach for granular media equations in the non-uniformly convex case, Probab. Theory Relat. Fields, 140, 19-40 (2008) · Zbl 1169.35031 · doi:10.1007/s00440-007-0056-3
[12] Chaintron, L.-P., Diez, A.: Propagation of chaos: a review of models, methods and applications. II. Applications, arXiv preprint arXiv:2106.14812 (2021)
[13] Chaintron, L.-P., Diez, A.: Propagation of chaos: a review of models, methods and applications. I. Models and methods, arXiv preprint arXiv:2203.00446 (2022) · Zbl 1496.82016
[14] Chizat, L., Bach, F.: On the global convergence of gradient descent for over-parameterized models using optimal transport. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems, pp 3040-3050 (2018)
[15] Collet, J-F; Malrieu, F., Logarithmic Sobolev inequalities for inhomogeneous Markov semigroups, ESAIM: Probab. Stat., 12, 492-504 (2008) · Zbl 1187.60059 · doi:10.1051/ps:2007042
[16] Dawson, DA, Critical dynamics and fluctuations for a mean-field model of cooperative behavior, J. Stat. Phys., 31, 1, 29-85 (1983) · doi:10.1007/BF01010922
[17] Del Moral, P.; Tugaut, J., Uniform propagation of chaos and creation of chaos for a class of nonlinear diffusions, Stoch. Anal. Appl., 37, 6, 909-935 (2019) · Zbl 1423.60122 · doi:10.1080/07362994.2019.1622426
[18] Delarue, F., Tse, A.: Uniform in time weak propagation of chaos on the torus, arXiv (2021)
[19] Delgadino, M.G., Gvalani, R.S., Pavliotis, G.A., Smith, S.A.: Phase transitions, logarithmic Sobolev inequalities, and uniform-in-time propagation of chaos for weakly interacting diffusions, arXiv preprint arXiv:2112.06304 (2021) · Zbl 07700884
[20] Diaconis, P.; Freedman, D., Finite exchangeable sequences, Ann. Probab., 8, 745-764 (1980) · Zbl 0434.60034 · doi:10.1214/aop/1176994663
[21] Durmus, A.; Eberle, A.; Guillin, A.; Zimmer, R., An elementary approach to uniform in time propagation of chaos, Proc. Am. Math. Soc., 148, 5387-5398 (2020) · Zbl 1471.60123 · doi:10.1090/proc/14612
[22] Figalli, A., Existence and uniqueness of martingale solutions for SDEs with rough or degenerate coefficients, J. Funct. Anal., 254, 1, 109-153 (2008) · Zbl 1169.60010 · doi:10.1016/j.jfa.2007.09.020
[23] Gautschi, W., Some elementary inequalities relating to the gamma and incomplete gamma function, J. Math. Phys., 38, 77-81 (1959) · Zbl 0094.04104 · doi:10.1002/sapm195938177
[24] Golse, F., On the dynamics of large particle systems in the mean field limit, Macroscopic and large scale phenomena: coarse graining, mean field limits and ergodicity, 1-144 (2016), Berlin: Springer, Berlin
[25] Gozlan, N.; Léonard, C., Transport inequalities: A survey, Markov Process. Relat. Fields, 16, 635-736 (2010) · Zbl 1229.26029
[26] Guillin, A., Le Bris, P., Monmarché, P.: Uniform in time propagation of chaos for the 2D vortex model and other singular stochastic systems, arXiv preprint arXiv:2108.08675 (2021) · Zbl 1504.60137
[27] Guillin, A., Liu, W., Wu, L. Zhang, C.: Uniform poincaré and logarithmic Sobolev inequalities for mean field particles systems, arXiv preprint arXiv:1909.07051 (2019)
[28] Guillin, A., Monmarche, P.: Uniform long-time and propagation of chaos estimates for mean field kinetic particles in non-convex landscapes. J. Stat. Phys. 185(15), 1-20 (2021) · Zbl 1515.82069
[29] Han, J., Hu, R., Long, J.: A class of dimensionality-free metrics for the convergence of empirical measures, arXiv preprint arXiv:2104.12036 (2021)
[30] Han, Y.: Entropic propagation of chaos for mean field diffusion with \(l_t^q-l_x^p\) interaction, linear growth interaction and fractional noise, arXiv preprint arXiv:2205.02772 (2022)
[31] Herrmann, S.; Tugaut, J., Non-uniqueness of stationary measures for self-stabilizing processes, Stoch. Process. Their Appl., 120, 7, 1215-1246 (2010) · Zbl 1197.60052 · doi:10.1016/j.spa.2010.03.009
[32] Jabin, P.-E., Poyato, D., Soler, J.: Mean-field limit of non-exchangeable systems, arXiv preprint arXiv:2112.15406 (2021)
[33] Jabin, P-E; Wang, Z., Mean field limit and propagation of chaos for Vlasov systems with bounded forces, J. Funct. Anal., 271, 12, 3588-3627 (2016) · Zbl 1388.60163 · doi:10.1016/j.jfa.2016.09.014
[34] Jabin, P-E; Wang, Z., Mean Field Limit for Stochastic Particle Systems, Active Particles, 379-402 (2017), Berlin: Springer, Berlin
[35] Jabin, P-E; Wang, Z., Quantitative estimates of propagation of chaos for stochastic systems with \({W}^{-1,\infty }\) kernels, Invent. Math., 214, 1, 523-591 (2018) · Zbl 1402.35208 · doi:10.1007/s00222-018-0808-y
[36] Jameson, GJO, Inequalities for gamma function ratios, Am. Math. Mon., 120, 936-940 (2013) · Zbl 1285.33004 · doi:10.4169/amer.math.monthly.120.10.936
[37] Kac, M.: Foundations of kinetic theory. In: Proceedings of The third Berkeley symposium on mathematical statistics and probability, vol. 3, University of California Press Berkeley and Los Angeles, California, pp. 171-197 (1956) · Zbl 0072.42802
[38] Lacker, D.: Hierarchies, entropy, and quantitative propagation of chaos for mean field diffusions (2021, preprint) · Zbl 1515.82109
[39] Lacker, D.: Quantitative approximate independence for continuous mean field gibbs measures. (2021, preprint) · Zbl 1484.82015
[40] Malrieu, F., Logarithmic sobolev inequalities for some nonlinear PDE’s, Stoch. Process. Their Appl., 95, 109-132 (2001) · Zbl 1059.60084 · doi:10.1016/S0304-4149(01)00095-3
[41] Malrieu, F., Convergence to equilibrium for granular media equations and their Euler schemes, Ann. Appl. Probab., 13, 2, 540-560 (2003) · Zbl 1031.60085 · doi:10.1214/aoap/1050689593
[42] McKean, H.P.: Propagation of chaos for a class of non-linear parabolic equations. In: Stochastic Differential Equations (Lecture Series in Differential Equations, Session 7, Catholic University, 1967), pp 41-57 (1967)
[43] Mei, S., Montanari, A., Nguyen, P.-M.: A mean field view of the landscape of two-layer neural networks. In: Proceedings of the National Academy of Sciences of the United States of America 115(33) (2018) · Zbl 1416.92014
[44] Otto, F.; Villani, C., Generalization of an inequality by Talagrand and links with the logarithmic Sobolev inequality, J. Funct. Anal., 173, 2, 361-400 (2000) · Zbl 0985.58019 · doi:10.1006/jfan.1999.3557
[45] Rosenzweig, M., Serfaty, S.: Global-in-time mean-field convergence for singular Riesz-type diffusive flows (2021). arXiv preprint arXiv:2108.09878 · Zbl 1516.35414
[46] Salem, S.: A gradient flow approach of uniform in time propagation of chaos for particles in double a well confinement (2018). arXiv preprint arXiv:1810.08946
[47] Salem, S., A gradient flow approach of propagation of chaos, Discrete Contin. Dyn. Syst., 40, 10, 5729 (2020) · Zbl 1454.60145 · doi:10.3934/dcds.2020243
[48] Salhi, J.; MacLaurin, J.; Toumi, S., On uniform propagation of chaos, Stochastics, 90, 1, 49-60 (2013) · Zbl 1498.60329 · doi:10.1080/17442508.2017.1311898
[49] Sirignano, J.; Spiliopoulos, K., Mean field analysis of neural networks: a law of large numbers, SIAM J. Appl. Math., 80, 2, 1 (2020) · Zbl 1440.60008 · doi:10.1137/18M1192184
[50] Sznitman, A-S, Topics in propagation of chaos, Ecole d’été de probabilités de Saint-Flour XIX-1989, 165-251 (1991), Berlin: Springer, Berlin · Zbl 0732.60114
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.