English
Related papers

Related papers: Oscillating solutions to the mean-field Langevin d…

200 papers

We give an example of a function satisfying a two-sided Polyak-Lojasiewicz condition but for which a gradient descent-ascent flow line fails to converge to the saddle point, circling around it instead. We can even impose the function to be…

Optimization and Control · Mathematics 2026-05-12 Jean-Christophe Mourrat

We study the mean-field Langevin descent-ascent (MFL-DA), a coupled optimization dynamics on the space of probability measures for entropically regularized two-player zero-sum games. Although the associated mean-field objective admits a…

Machine Learning · Computer Science 2026-02-03 Geuntaek Seo , Minseop Shin , Pierre Monmarché , Beomjun Choi

Recent results have shown that for two-layer fully connected neural networks, gradient flow converges to a global optimum in the infinite width limit, by making a connection between the mean field dynamics and the Wasserstein gradient flow.…

Optimization and Control · Mathematics 2020-07-16 Walid Krichene , Kenneth F. Caluya , Abhishek Halder

We investigate the convergence properties of a continuous-time optimization method, the \textit{Mean-Field Best Response} flow, for solving convex-concave min-max games with entropy regularization. We introduce suitable Lyapunov functions…

Optimization and Control · Mathematics 2025-03-11 Razvan-Andrei Lascu , Mateusz B. Majka , Łukasz Szpruch

We study the local convergence of diffusive mean-field systems, including Wasserstein gradient flows, min-max dynamics, and multi-species games. We establish exponential local convergence in $\chi^2$-divergence with sharp rates, under two…

Optimization and Control · Mathematics 2026-02-13 Guillaume Wang , Lénaïc Chizat

We consider the coupling between two networks, each having N nodes whose individual dynamics is modeled by a two-state master equation. The intra-network interactions are all to all, whereas the inter-network interactions involve only a…

Adaptation and Self-Organizing Systems · Physics 2015-08-14 Malgorzata Turalska , Adam Svenkeson , Bruce J. West

The mean-field Langevin dynamics (MFLD) minimizes an entropy-regularized nonlinear convex functional on the Wasserstein space over $\mathbb{R}^d$, and has gained attention recently as a model for the gradient descent dynamics of interacting…

Machine Learning · Computer Science 2026-05-19 Anming Gu , Juno Kim

As an example of the nonlinear Fokker-Planck equation, the mean field Langevin dynamics recently attracts attention due to its connection to (noisy) gradient descent on infinitely wide neural networks in the mean field regime, and hence the…

Analysis of PDEs · Mathematics 2025-09-04 Mohamed Alfaki Aboubacrine Assadek

Two-dimensional correlation functions in $\Delta\eta-\Delta \phi$ for charged hadrons emitted in heavy-ion collisions are calculated in event-by-event hydrodynamics. With the Glauber model for the initial density distributions in the…

Nuclear Theory · Physics 2015-06-11 Piotr Bozek , Wojciech Broniowski

This work is mainly concerned with the so-called limit theory for mean-field games. Adopting the weak formulation paradigm put forward by Carmona and Lacker, we consider a fully non-Markovian setting allowing for drift control and…

Probability · Mathematics 2023-12-25 Dylan Possamaï , Ludovic Tangpi

The coupled Maxwell-Lorentz system describes feed-back action of electromagnetic fields in classical electrodynamics. When applied to point-charge sources (viewed as limiting cases of charged fluids) the resulting nonlinear weakly…

Analysis of PDEs · Mathematics 2007-05-23 Guenther Hoermann , Michael Kunzinger

In this paper, we extend mean-field Langevin dynamics to minimax optimization over probability distributions for the first time with symmetric and provably convergent updates. We propose mean-field Langevin averaged gradient (MFL-AG), a…

Optimization and Control · Mathematics 2024-02-19 Juno Kim , Kakei Yamamoto , Kazusato Oko , Zhuoran Yang , Taiji Suzuki

We consider an energy functional combining the square of the local oscillation of a one--dimensional function with a double well potential. We establish the existence of minimal heteroclinic solutions connecting the two wells of the…

Analysis of PDEs · Mathematics 2018-11-20 Annalisa Cesaroni , Serena Dipierro , Matteo Novaga , Enrico Valdinoci

We prove regularity, global existence, and convergence of Lagrangian mean curvature flows in the two-convex case. Such results were previously only known in the convex case, of which the current work represents a significant improvement.…

Differential Geometry · Mathematics 2023-12-22 Chung-Jun Tsai , Mao-Pei Tsui , Mu-Tao Wang

We introduce a novel reformulation of the mean-field system for pulse-coupled oscillators. It is based on writing a closed equation for the inverse distribution function associated to the probability density of oscillators with a given…

Analysis of PDEs · Mathematics 2024-04-23 José Antonio Carrillo , Xu'an Dou , Pierre Roux , Zhennan Zhou

We investigate the convergence of McKean-Vlasov diffusions in a nonconvex landscape. These processes are linked to nonlinear partial differential equations. According to our previous results, there are at least three stationary measures…

Probability · Mathematics 2013-05-27 Julian Tugaut

We consider a gradient flow related to the mean field type equation. First, we show that this flow exists for all time. Next, we prove a compactness result for this flow allowing us to get, under suitable hypothesis on its energy, the…

Analysis of PDEs · Mathematics 2012-12-11 Jean-Baptiste Castéras

Lagrangian motions of fluid particles in a general velocity field oscillating in time are studied with the use of the two-timing method. Our aims are: (i) to calculate systematically the most general and practically usable asymptotic…

Fluid Dynamics · Physics 2015-09-22 Vladimir A. Vladimirov

In this paper, we study the stability and convergence of continuous-time Lagrangian saddle flows to solutions of a convex constrained optimization problem. Convergence of these flows is well-known when the underlying saddle function is…

Optimization and Control · Mathematics 2020-10-20 Adrian Hauswirth , Lukas Ortmann , Saverio Bolognani , Florian Dörfler

We investigate the non-Langevin relative of the L\'{e}vy-driven Langevin random system, under an assumption that both systems share a common (asymptotic, stationary, steady-state) target pdf. The relaxation to equilibrium in the fractional…

Statistical Mechanics · Physics 2020-10-22 P. Garbaczewski , M. Zaba
‹ Prev 1 2 3 10 Next ›