English
Related papers

Related papers: Mirror Mean-Field Langevin Dynamics

200 papers

We present new policy mirror descent (PMD) methods for solving reinforcement learning (RL) problems with either strongly convex or general convex regularizers. By exploring the structural properties of these overall highly nonconvex…

Machine Learning · Computer Science 2022-04-08 Guanghui Lan

In this paper, we study the problem of sampling from a given probability density function that is known to be smooth and strongly log-concave. We analyze several methods of approximate sampling based on discretizations of the (highly…

Statistics Theory · Mathematics 2024-02-26 Arnak S. Dalalyan , Avetik G. Karagulyan

We investigate the global numerical approximation of a class of extended mean field control problems (MFC), where the dynamics and costs depend on the joint distribution of the state and the control. We propose a framework to approximate…

Optimization and Control · Mathematics 2026-03-23 Athena Picarelli , Marco Scaratti , Jonathan Tam

We develop an exhaustive study of Markov decision process (MDP) under mean field interaction both on states and actions in the presence of common noise, and when optimization is performed over open-loop controls on infinite horizon. Such…

Optimization and Control · Mathematics 2021-09-10 Médéric Motte , Huyên Pham

In this paper, we revisit the recently established theoretical guarantees for the convergence of the Langevin Monte Carlo algorithm of sampling from a smooth and (strongly) log-concave density. We improve the existing results when the…

Statistics Theory · Mathematics 2017-07-31 Arnak S. Dalalyan

We study the problem of sampling from a distribution $\target$ using the Langevin Monte Carlo algorithm and provide rate of convergences for this algorithm in terms of Wasserstein distance of order $2$. Our result holds as long as the…

Computation · Statistics 2016-07-04 Thomas Bonis

We study Langevin-type algorithms for sampling from Gibbs distributions such that the potentials are dissipative and their weak gradients have finite moduli of continuity not necessarily convergent to zero. Our main result is a…

Statistics Theory · Mathematics 2024-03-01 Shogo Nakakita

In this paper, we explore a general Aggregated Gradient Langevin Dynamics framework (AGLD) for the Markov Chain Monte Carlo (MCMC) sampling. We investigate the nonasymptotic convergence of AGLD with a unified analysis for different data…

Machine Learning · Computer Science 2019-10-22 Chao Zhang , Jiahao Xie , Zebang Shen , Peilin Zhao , Tengfei Zhou , Hui Qian

The mean-field theory (MFT) of simple glasses, which is exact in the limit of infinite spatial dimensions, $d\rightarrow\infty$, offers theoretical insight as well as quantitative predictions about certain features of $d=3$ systems. In…

Disordered Systems and Neural Networks · Physics 2024-05-27 Patrick Charbonneau , Yi Hu , Peter K. Morse

We consider the problem of learning the optimal policy for infinite-horizon Markov decision processes (MDPs). For this purpose, some variant of Stochastic Mirror Descent is proposed for convex programming problems with Lipschitz-continuous…

Optimization and Control · Mathematics 2022-03-01 Daniil Tiapkin , Alexander Gasnikov

In molecular dynamics, penalized overdamped Langevin dynamics are used to model the motion of a set of particles that follow constraints up to a parameter $\varepsilon$. The most used schemes for simulating these dynamics are the Euler…

Numerical Analysis · Mathematics 2022-10-10 Adrien Laurent

We demonstrate the versatility of mean-field games (MFGs) as a mathematical framework for explaining, enhancing, and designing generative models. In generative flows, a Lagrangian formulation is used where each particle (generated sample)…

Machine Learning · Statistics 2023-10-25 Benjamin J. Zhang , Markos A. Katsoulakis

The Fokker-Planck (FP) equation governs the evolution of densities for stochastic dynamics of physical systems, such as the Langevin dynamics and the Lorenz system. This work simulates FP equations through a mean field control (MFC)…

Optimization and Control · Mathematics 2025-08-06 Mo Zhou , Stanley Osher , Wuchen Li

We study two variants of the mirror descent-ascent (MDA) algorithm for solving min-max problems on the space of measures: simultaneous and alternating. We work under assumptions of convexity-concavity and relative smoothness of the payoff…

Optimization and Control · Mathematics 2026-05-08 Razvan-Andrei Lascu , Mateusz B. Majka , Łukasz Szpruch

The multivariate normal density is a monotonic function of the distance to the mean, and its ellipsoidal shape is due to the underlying Euclidean metric. We suggest to replace this metric with a locally adaptive, smoothly changing…

Machine Learning · Statistics 2016-09-26 Georgios Arvanitidis , Lars Kai Hansen , Søren Hauberg

Finding Nash equilibria in two-player zero-sum continuous games is a central problem in machine learning, e.g. for training both GANs and robust models. The existence of pure Nash equilibria requires strong conditions which are not…

Machine Learning · Computer Science 2021-05-07 Carles Domingo-Enrich , Samy Jelassi , Arthur Mensch , Grant Rotskoff , Joan Bruna

We revisit the problem of sampling from a target distribution that has a smooth strongly log-concave density everywhere in $\mathbb R^p$. In this context, if no additional density information is available, the randomized midpoint…

Statistics Theory · Mathematics 2023-06-19 Lu Yu , Avetik Karagulyan , Arnak Dalalyan

In this paper we consider a new probability sampling methods based on Langevin diffusion dynamics to resolve the problem of existing Monte Carlo algorithms when draw samples from high dimensional target densities. We extent…

Machine Learning · Computer Science 2025-03-31 Z. Zarezadeh , N. Zarezadeh

We propose a microscopic stochastic approach to improve description of nuclear dynamics beyond the mean-field approximation at low energies. It is shown that, for small amplitude fluctuations, the proposed model gives a result for the…

Nuclear Theory · Physics 2009-11-13 Sakir Ayik

Many tasks in machine learning and signal processing can be solved by minimizing a convex function of a measure. This includes sparse spikes deconvolution or training a neural network with a single hidden layer. For these problems, we study…

Optimization and Control · Mathematics 2018-10-30 Lenaic Chizat , Francis Bach