English
Related papers

Related papers: Improved Particle Approximation Error for Mean Fie…

200 papers

We study the problem of policy optimization for infinite-horizon discounted Markov Decision Processes with softmax policy and nonlinear function approximation trained with policy gradient algorithms. We concentrate on the training dynamics…

Machine Learning · Computer Science 2020-10-23 Andrea Agazzi , Jianfeng Lu

Most works on federated learning (FL) focus on the most common frequentist formulation of learning whereby the goal is minimizing the global empirical loss. Frequentist learning, however, is known to be problematic in the regime of limited…

Information Theory · Computer Science 2022-06-13 Dongzhu Liu , Osvaldo Simeone

In this paper, we study the fundamental statistical efficiency of Reinforcement Learning in Mean-Field Control (MFC) and Mean-Field Game (MFG) with general model-based function approximation. We introduce a new concept called Mean-Field…

Machine Learning · Computer Science 2024-10-04 Jiawei Huang , Batuhan Yardim , Niao He

We study reinforcement learning with linear function approximation where the transition probability and reward functions are linear with respect to a feature mapping $\boldsymbol{\phi}(s,a)$. Specifically, we consider the episodic…

Machine Learning · Computer Science 2023-01-31 Pihe Hu , Yu Chen , Longbo Huang

We develop a mathematically rigorous framework for multilayer neural networks in the mean field regime. As the network's widths increase, the network's learning trajectory is shown to be well captured by a meaningful and dynamically…

Machine Learning · Computer Science 2023-02-14 Phan-Minh Nguyen , Huy Tuan Pham

The filtering distribution in hidden Markov models evolves according to the law of a mean-field model in state-observation space. The ensemble Kalman filter (EnKF) approximates this mean-field model with an ensemble of interacting…

Machine Learning · Statistics 2025-12-25 Eviatar Bach , Ricardo Baptista , Edoardo Calvello , Bohan Chen , Andrew Stuart

We consider distributed optimization under communication constraints for training deep learning models. We propose a new algorithm, whose parameter updates rely on two forces: a regular gradient step, and a corrective direction dictated by…

Machine Learning · Computer Science 2022-04-29 Yunfei Teng , Wenbo Gao , Francois Chalus , Anna Choromanska , Donald Goldfarb , Adrian Weller

Regularized Markov Decision Processes serve as models of sequential decision making under uncertainty wherein the decision maker has limited information processing capacity and/or aversion to model ambiguity. With functional approximation,…

Artificial Intelligence · Computer Science 2025-02-11 Jiachen Xi , Alfredo Garcia , Petar Momcilovic

The mean field approximation to the Ising model is a canonical variational tool that is used for analysis and inference in Ising models. We provide a simple and optimal bound for the KL error of the mean field approximation for Ising models…

Machine Learning · Computer Science 2018-02-22 Vishesh Jain , Frederic Koehler , Elchanan Mossel

Priors with non-smooth log-densities, such as the l1-prior, are widely used in Bayesian inverse problems for their sparsity-inducing properties. Existing Langevin-based sampling methods typically rely on proximal mappings or smooth…

Numerical Analysis · Mathematics 2026-05-05 Ivan Cheltsov , Federico Cornalba , Clarice Poon , Tony Shardlow

Integration against a probability distribution given its unnormalized density is a central task in Bayesian inference and other fields. We introduce new methods for approximating such expectations with a small set of weighted samples --…

Machine Learning · Statistics 2026-05-15 Ayoub Belhadji , Daniel Sharp , Youssef M. Marzouk

Replica exchange stochastic gradient Langevin dynamics (reSGLD) has shown promise in accelerating the convergence in non-convex learning; however, an excessively large correction for avoiding biases from noisy energy estimators has limited…

Machine Learning · Statistics 2021-03-19 Wei Deng , Qi Feng , Georgios Karagiannis , Guang Lin , Faming Liang

Langevin Dynamics is a Stochastic Differential Equation (SDE) central to sampling and generative modeling and is implemented via time discretization. Langevin Monte Carlo (LMC), based on the Euler-Maruyama discretization, is the simplest…

Machine Learning · Computer Science 2025-10-10 Saravanan Kandasamy , Dheeraj Nagaraj

Acceleration is a celebrated cornerstone of convex optimization, enabling gradient-based algorithms to converge sublinearly in the condition number. A major open question is whether an analogous acceleration phenomenon is possible for…

Probability · Mathematics 2026-04-01 Jason M. Altschuler , Sinho Chewi , Matthew S. Zhang

In this paper, we present an innovative particle system characterized by moderate interactions, designed to accurately approximate kinetic flocking models that incorporate singular interaction forces and local alignment mechanisms. We…

Analysis of PDEs · Mathematics 2024-04-23 Jinhuan Wang , Keyu Li , Hui Huang

Approximate Bayesian inference estimates descriptors of an intractable target distribution - in essence, an optimization problem within a family of distributions. For example, Langevin dynamics (LD) extracts asymptotically exact samples…

Machine Learning · Statistics 2021-10-11 Zheyang Shen , Markus Heinonen , Samuel Kaski

We consider Langevin dynamics associated with a modified kinetic energy vanishing for small momenta. This allows us to freeze slow particles, and hence avoid the re-computation of inter-particle forces, which leads to computational gains.…

Statistical Mechanics · Physics 2016-07-20 Stephane Redon , Gabriel Stoltz , Zofia Trstanova

For quasi-linear interface problems with discontinuous diffusion coefficients, the nonconvex objective functional often leads to optimization stagnation in randomized neural network approximations. This paper Proposes a…

Numerical Analysis · Mathematics 2026-02-06 Siyuan Lang , Zhiyue Zhang

In recent years, even though Stochastic Gradient Descent (SGD) and its variants are well-known for training neural networks, it suffers from limitations such as the lack of theoretical guarantees, vanishing gradients, and excessive…

Optimization and Control · Mathematics 2022-02-17 Junxiang Wang , Hongyi Li , Liang Zhao

Langevin diffusion (LD) is one of the main workhorses for sampling problems. However, its convergence rate can be significantly reduced if the target distribution is a mixture of multiple densities, especially when each component…

Probability · Mathematics 2020-07-14 Jing Dong , Xin T. Tong