中文
相关论文

相关论文: Convex Analysis of the Mean Field Langevin Dynamic…

200 篇论文

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…

偏微分方程分析 · 数学 2025-09-04 Mohamed Alfaki Aboubacrine Assadek

The mean-field Langevin dynamics (MFLD) is a nonlinear generalization of the Langevin dynamics that incorporates a distribution-dependent drift, and it naturally arises from the optimization of two-layer neural networks via (noisy) gradient…

机器学习 · 计算机科学 2023-06-13 Taiji Suzuki , Denny Wu , Atsushi Nitanda

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…

机器学习 · 计算机科学 2026-05-19 Anming Gu , Juno Kim

Our work is motivated by a desire to study the theoretical underpinning for the convergence of stochastic gradient type algorithms widely used for non-convex learning tasks such as training of neural networks. The key insight, already…

概率论 · 数学 2020-12-15 Kaitong Hu , Zhenjie Ren , David Siska , Lukasz Szpruch

Gradient Langevin dynamics and a variety of its variants have attracted increasing attention owing to their convergence towards the global optimal solution, initially in the unconstrained convex framework while recently even in convex…

最优化与控制 · 数学 2024-08-15 Kanji Sato , Akiko Takeda , Reiichiro Kawai , Taiji Suzuki

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…

最优化与控制 · 数学 2022-08-12 Lénaïc Chizat

Mean-field Langevin dynamics (MFLD) minimizes an entropy-regularized nonlinear convex functional defined over the space of probability distributions. MFLD has gained attention due to its connection with noisy gradient descent for mean-field…

机器学习 · 计算机科学 2024-10-31 Atsushi Nitanda

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…

概率论 · 数学 2025-04-28 Axel Ringh , Akash Sharma

An improved method for driving a system into a desired distribution, for example, the Gibbs-Boltzmann distribution, is proposed, which makes use of an artificial relaxation process. The standard techniques for achieving the Gibbs-Boltzmann…

统计力学 · 物理学 2015-06-18 Masayuki Ohzeki , Akihisa Ichiki

The stochastic gradient Langevin Dynamics is one of the most fundamental algorithms to solve sampling problems and non-convex optimization appearing in several machine learning applications. Especially, its variance reduced versions have…

机器学习 · 计算机科学 2022-11-22 Yuri Kinoshita , Taiji Suzuki

We introduce a new theoretical framework to analyze deep learning optimization with connection to its generalization error. Existing frameworks such as mean field theory and neural tangent kernel theory for neural network optimization…

机器学习 · 计算机科学 2020-10-28 Taiji Suzuki

We consider the problem of sampling from a target distribution, which is \emph {not necessarily logconcave}, in the context of empirical risk minimization and stochastic optimization as presented in Raginsky et al. (2017). Non-asymptotic…

统计理论 · 数学 2021-02-03 Ngoc Huy Chau , Éric Moulines , Miklos Rásonyi , Sotirios Sabanis , Ying Zhang

We study the long time behavior of an underdamped mean-field Langevin (MFL) equation, and provide a general convergence as well as an exponential convergence rate result under different conditions. The results on the MFL equation can be…

概率论 · 数学 2023-11-28 Anna Kazeykina , Zhenjie Ren , Xiaolu Tan , Junjian Yang

We study the Langevin dynamics of diffusive particles with regular pairwise interactions under mean-field scaling. By approximating empirical distributions with conditional distributions, we establish coercive and contractive properties for…

概率论 · 数学 2026-05-28 Songbo Wang

The usual Langevin approach to describe systems driven by noise fails to describe the long time behavior of systems with multiple attractors. The solution of the associated linear Fokker-Planck equation is always unique, even though it…

统计力学 · 物理学 2017-06-20 M. Morillo , J. M. Casado

We propose a new method called the N-particle underdamped Langevin algorithm for optimizing a special class of non-linear functionals defined over the space of probability measures. Examples of problems with this formulation include…

统计计算 · 统计学 2024-02-07 Qiang Fu , Ashia Wilson

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…

最优化与控制 · 数学 2024-02-19 Juno Kim , Kakei Yamamoto , Kazusato Oko , Zhuoran Yang , Taiji Suzuki

We present a unified framework to analyze the global convergence of Langevin dynamics based algorithms for nonconvex finite-sum optimization with $n$ component functions. At the core of our analysis is a direct analysis of the ergodicity of…

机器学习 · 统计学 2020-10-20 Pan Xu , Jinghui Chen , Difan Zou , Quanquan Gu

We provide a framework to analyze the convergence of discretized kinetic Langevin dynamics for $M$-$\nabla$Lipschitz, $m$-convex potentials. Our approach gives convergence rates of $\mathcal{O}(m/M)$, with explicit stepsize restrictions,…

数值分析 · 数学 2024-05-24 Benedict Leimkuhler , Daniel Paulin , Peter A. Whalley

Non-convex sampling is a key challenge in machine learning, central to non-convex optimization in deep learning as well as to approximate probabilistic inference. Despite its significance, theoretically there remain many important…

机器学习 · 计算机科学 2024-09-18 Mohammad Reza Karimi , Ya-Ping Hsieh , Andreas Krause
‹ 上一页 1 2 3 10 下一页 ›