paper-with-me

Papers

Mean Field Optimization Problem Regularized by Fisher Information

2023-02-12 · Julien Claisse, Giovanni Conforti, Zhenjie Ren, SongBo Wang

Recently there is a rising interest in the research of mean field optimization, in particular because of its role in analyzing the training of neural networks. In this paper by adding the Fisher Information as the regularizer, we relate the regularized mean field optimization problem to a so-called mean field Schrodinger dynamics. We develop an energy-dissipation method to show that the marginal distributions of the mean field Schrodinger dynamics converge exponentially quickly towards the unique minimizer of the regularized optimization problem. Remarkably, the mean field Schrodinger dynamics is proved to be a gradient flow on the probability measure space with respect to the relative entropy. Finally we propose a Monte Carlo method to sample the marginal distributions of the mean field Schrodinger dynamics.

📄 PDF Abstract BibTeX arXiv:2302.05938

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

On propagation of chaos for the Fisher-Rao gradient flow in entropic mean-field optimization

2026-02-16 · Petra Lazić, Linshan Liu, Mateusz B. Majka arxiv

We consider a class of optimization problems on the space of probability measures motivated by the mean-field approach to studying neural networks. Such problems can be solved by constructing continuous-time gradient flo…

Fisher Discriminative Least Squares Regression for Image Classification

2019-03-19 · Zhe Chen, Xiao-Jun Wu, Josef Kittler

Discriminative least squares regression (DLSR) has been shown to achieve promising performance in multi-class image classification tasks. Its key idea is to force the regression labels of different classes to move in opp…

ClassificationFace RecognitionGeneral Classificationimage-classification+2

SOFIM: Stochastic Optimization Using Regularized Fisher Information Matrix

2024-03-05 · Mrinmay Sen, A. K. Qin, Gayathri C, Raghu Kishore N 외

This paper introduces a new stochastic optimization method based on the regularized Fisher information matrix (FIM), named SOFIM, which can efficiently utilize the FIM to approximate the Hessian matrix for finding Newton…

image-classificationImage ClassificationStochastic Optimization

A Fisher-Rao gradient flow for entropic mean-field min-max games

2024-05-24 · Razvan-Andrei Lascu, Mateusz B. Majka, Łukasz Szpruch

Gradient flows play a substantial role in addressing many machine learning problems. We examine the convergence in continuous-time of a \textit{Fisher-Rao} (Mean-Field Birth-Death) gradient flow in the context of solving…

Learning Regularized Monotone Graphon Mean-Field Games

2023-10-12 · NeurIPS 2023 11

This paper studies two fundamental problems in regularized Graphon Mean-Field Games (GMFGs). First, we establish the existence of a Nash Equilibrium (NE) of any $\lambda$-regularized GMFG (for $\lambda\geq 0$). This resu…