Bayesian Neural Networks: A Min-Max Game Framework

2023/11/18 by Junping Hong, Hong, Junping, Erçan E. Kuruoğlu +1
Computer Science · #Machine Learning and Algorithms #Neural Networks and Applications #Machine Learning and Data Classification

paper · pdf · doi:10.48550/arxiv.2311.11126

Abstract

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.

Related

• Masked Bayesian Neural Networks : Theoretical Guarantee and its Posterior Inference
• A Limited-Capacity Minimax Theorem for Non-Convex Games or: How I Learned to Stop Worrying about Mixed-Nash and Love Neural Nets
• Generative Adversarial Networks are Special Cases of Artificial Curiosity (1990) and also Closely Related to Predictability Minimization (1991)
• Masked Bayesian Neural Networks : Computation and Optimality
• Solving Neural Min-Max Games: The Role of Architecture, Initialization & Dynamics