paper-with-me

홈 › Papers

Convex Analysis of the Mean Field Langevin Dynamics

2022-01-25 · Atsushi Nitanda, Denny Wu, Taiji Suzuki

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 convergence property of the dynamics is of great theoretical interest. In this work, we give a concise and self-contained convergence rate analysis of the mean field Langevin dynamics with respect to the (regularized) objective function in both continuous and discrete time settings. The key ingredient of our proof is a proximal Gibbs distribution $p_q$ associated with the dynamics, which, in combination with techniques in [Vempala and Wibisono (2019)], allows us to develop a simple convergence theory parallel to classical results in convex optimization. Furthermore, we reveal that $p_q$ connects to the duality gap in the empirical risk minimization setting, which enables efficient empirical evaluation of the algorithm convergence.

📄 PDF Abstract BibTeX arXiv:2201.10469

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Mirror Mean-Field Langevin Dynamics

2025-05-05 · Anming Gu, Juno Kim

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 dyn…

Uniform-in-time propagation of chaos for mean field Langevin dynamics

2022-12-06 · Fan Chen, Zhenjie Ren, SongBo Wang

We study the mean field Langevin dynamics and the associated particle system. By assuming the functional convexity of the energy, we obtain the $L^p$-convergence of the marginal distributions towards the unique invariant…

On the Convergence of Min-Max Langevin Dynamics and Algorithm

2024-12-29 · Yang Cai, Siddharth Mitra, Xiuyuan Wang, Andre Wibisono

We study zero-sum games in the space of probability distributions over the Euclidean space $\mathbb{R}^d$ with entropy regularization, in the setting when the interaction function between the players is smooth and strong…

Mean-field Langevin dynamics: Time-space discretization, stochastic gradient, and variance reduction

2023-09-21 · NeurIPS 2023 11

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 …

Convergence of mean-field Langevin dynamics: Time and space discretization, stochastic gradient, and variance reduction

2023-06-12 · Taiji Suzuki, Denny Wu, Atsushi Nitanda

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 …