导航
学术宝威体育(中国)集团有限公司|
宝威体育(中国)集团有限公司题目: Self-interacting approximation to McKean-Vlasov long time limit
报 告 人: 任振杰 博士
宝威体育(中国)集团有限公司人所在单位: 巴黎第九大学
宝威体育(中国)集团有限公司日期: 2024-04-16
宝威体育(中国)集团有限公司时间: 10:30-11:30
宝威体育(中国)集团有限公司地点: 光华楼东主楼2001
   
宝威体育(中国)集团有限公司摘要:

Motivated by the mean-field optimization model of the training of two-layer neural networks, we propose a novel method to approximate the invariant measures of a class of McKean-Vlasov diffusions. We introduce a proxy process that substitutes the mean-field interaction with self-interaction through a weighted occupation measure of the particle's past. If the McKean-Vlasov diffusion is the gradient flow of a convex mean-field potential functional, we show that the self-interacting process exponentially converges towards its unique invariant measure close to that of the McKean-Vlasov diffusion. As an application, we show how to learn the optimal weights of a two-layer neural network by training a single neuron.

学术海报.pdf

   
本年度学院宝威体育(中国)集团有限公司总序号: 1106

Copyright © |2012 宝威体育(中国)集团有限公司版权所有 沪ICP备042465