Bayesian Neural Networks: A Min-Max Game Framework

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Hong, Junping, Kuruoglu, Ercan Engin
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910719191023616
author Hong, Junping
Kuruoglu, Ercan Engin
author_facet Hong, Junping
Kuruoglu, Ercan Engin
contents In deep learning, Bayesian neural networks (BNN) provide the role of robustness analysis, and the minimax method is used to be a conservative choice in the traditional Bayesian field. In this paper, we study a conservative BNN with the minimax method and formulate a two-player game between a deterministic neural network $f$ and a sampling stochastic neural network $f + r*ξ$. From this perspective, we understand the closed-loop neural networks with the minimax loss and reveal their connection to the BNN. We test the models on simple data sets, study their robustness under noise perturbation, and report some issues for searching $r$.
format Preprint
id arxiv_https___arxiv_org_abs_2311_11126
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Bayesian Neural Networks: A Min-Max Game Framework
Hong, Junping
Kuruoglu, Ercan Engin
Machine Learning
Artificial Intelligence
In deep learning, Bayesian neural networks (BNN) provide the role of robustness analysis, and the minimax method is used to be a conservative choice in the traditional Bayesian field. In this paper, we study a conservative BNN with the minimax method and formulate a two-player game between a deterministic neural network $f$ and a sampling stochastic neural network $f + r*ξ$. From this perspective, we understand the closed-loop neural networks with the minimax loss and reveal their connection to the BNN. We test the models on simple data sets, study their robustness under noise perturbation, and report some issues for searching $r$.
title Bayesian Neural Networks: A Min-Max Game Framework
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2311.11126