English
Related papers

Related papers: Symmetric Mean-field Langevin Dynamics for Distrib…

200 papers

We study policy optimization in Stackelberg mean field games (MFGs), a hierarchical framework for modeling the strategic interaction between a single leader and an infinitely large population of homogeneous followers. The objective can be…

Machine Learning · Computer Science 2025-11-27 Sihan Zeng , Benjamin Patrick Evans , Sujay Bhatt , Leo Ardon , Sumitra Ganesh , Alec Koppel

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

Noisy particle gradient descent (NPGD) is an algorithm to minimize convex functions over the space of measures that include an entropy term. In the many-particle limit, this algorithm is described by a Mean-Field Langevin dynamics - a…

Optimization and Control · Mathematics 2022-08-12 Lénaïc Chizat

We study the complexity of sampling from the stationary distribution of a mean-field SDE, or equivalently, the complexity of minimizing a functional over the space of probability measures which includes an interaction term. Our main insight…

Statistics Theory · Mathematics 2024-07-08 Yunbum Kook , Matthew S. Zhang , Sinho Chewi , Murat A. Erdogdu , Mufan Bill Li

Markov Chain Monte Carlo (MCMC) is one of the most powerful methods to sample from a given probability distribution, of which the Metropolis Adjusted Langevin Algorithm (MALA) is a variant wherein the gradient of the distribution is used…

Applications · Statistics 2022-01-21 Mariya Mamajiwala , Debasish Roy , Serge Guillas

We develop a convex analysis approach for solving LQG optimal control problems and apply it to major-minor (MM) LQG mean-field game (MFG) systems. The approach retrieves the best response strategies for the major agent and all minor agents…

Systems and Control · Computer Science 2020-06-15 Dena Firoozi , Sebastian Jaimungal , Peter E. Caines

We study a variant of a recently introduced min-max optimization framework where the max-player is constrained to update its parameters in a greedy manner until it reaches a first-order stationary point. Our equilibrium definition for this…

Machine Learning · Computer Science 2022-07-04 Vijay Keswani , Oren Mangoubi , Sushant Sachdeva , Nisheeth K. Vishnoi

We study multi-agent reinforcement learning (MARL) for the general-sum Markov Games (MGs) under the general function approximation. In order to find the minimum assumption for sample-efficient learning, we introduce a novel complexity…

Machine Learning · Computer Science 2023-10-11 Nuoya Xiong , Zhihan Liu , Zhaoran Wang , Zhuoran Yang

Many tasks in modern machine learning can be formulated as finding equilibria in \emph{sequential} games. In particular, two-player zero-sum sequential games, also known as minimax optimization, have received growing interest. It is…

Machine Learning · Computer Science 2019-11-26 Yuanhao Wang , Guodong Zhang , Jimmy Ba

In this paper, we consider nonconvex minimax optimization, which is gaining prominence in many modern machine learning applications such as GANs. Large-scale edge-based collection of training data in these applications calls for…

Optimization and Control · Mathematics 2022-03-10 Pranay Sharma , Rohan Panda , Gauri Joshi , Pramod K. Varshney

Reinforcement learning is a powerful tool to learn the optimal policy of possibly multiple agents by interacting with the environment. As the number of agents grow to be very large, the system can be approximated by a mean-field problem.…

Optimization and Control · Mathematics 2020-08-18 Weichen Wang , Jiequn Han , Zhuoran Yang , Zhaoran Wang

Stochastic Gradient Langevin Dynamics (SGLD) is a powerful algorithm for optimizing a non-convex objective, where a controlled and properly scaled Gaussian noise is added to the stochastic gradients to steer the iterates towards a global…

Optimization and Control · Mathematics 2020-06-04 Yuanhan Hu , Xiaoyu Wang , Xuefeng Gao , Mert Gurbuzbalaban , Lingjiong Zhu

The Distributional Alignment Game framework provides a powerful variational perspective on Answer-Level Fine-Tuning (ALFT). However, standard algorithms for these games rely on estimating logarithmic rewards from small batches, introducing…

Machine Learning · Computer Science 2026-05-05 Mehryar Mohri , Jon Schneider , Yutao Zhong

Normalizing flows (NF) use a continuous generator to map a simple latent (e.g. Gaussian) distribution, towards an empirical target distribution associated with a training data set. Once trained by minimizing a variational objective, the…

Machine Learning · Statistics 2023-05-23 Florentin Coeurdoux , Nicolas Dobigeon , Pierre Chainais

Langevin dynamics has found a large number of applications in sampling, optimization and estimation. Preconditioning the gradient in the dynamics with the covariance - an idea that originated in literature related to solving estimation and…

Probability · Mathematics 2025-04-28 Axel Ringh , Akash Sharma

Methods that align distributions by minimizing an adversarial distance between them have recently achieved impressive results. However, these approaches are difficult to optimize with gradient descent and they often do not converge well…

Machine Learning · Computer Science 2018-02-01 Ben Usman , Kate Saenko , Brian Kulis

We address a multi-class traffic model, for which we computationally assess the ability of mean-field games (MFGs) to yield approximate Nash equilibria for traffic flow games of intractable large finite-players. We introduce ad hoc…

Optimization and Control · Mathematics 2025-03-28 Amal Machtalay , Abderrahmane Habbal , Ahmed Ratnani , Imad Kissami

We propose an adaptively weighted stochastic gradient Langevin dynamics algorithm (SGLD), so-called contour stochastic gradient Langevin dynamics (CSGLD), for Bayesian learning in big data statistics. The proposed algorithm is essentially a…

Machine Learning · Statistics 2022-05-24 Wei Deng , Guang Lin , Faming Liang

We study distributed versions of Markov Chain Monte Carlo (MCMC) algorithms for generating random $k$-colorings of an input graph with maximum degree $\Delta$. In the sequential setting, the Glauber dynamics is the simple MCMC algorithm…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-07-29 Charlie Carlson , Daniel Frishberg , Eric Vigoda

We study the simulated annealing algorithm based on the kinetic Langevin dynamics, in order to find the global minimum of a non-convex potential function. For both the continuous time formulation and a discrete time analogue, we obtain the…

Probability · Mathematics 2022-06-14 Xuedong He , Xiaolu Tan , Ruocheng Wu