Detailed Information

Masked Bayesian Neural Networks: Theoretical Guarantee and its Posterior Inference

Cited 0 time in Web of Science Cited 1 time in Scopus

Kong, Insung; Yang, Dongyoon; Lee, Jongjin; Ohn, Ilsang; Baek, Gyuseung; Kim, Yongdai

Issue Date
ML Research Press
Proceedings of Machine Learning Research, Vol.202, pp.17462-17491
Bayesian approaches for learning deep neural networks (BNN) have been received much attention and successfully applied to various applications. Particularly, BNNs have the merit of having better generalization ability as well as better uncertainty quantification. For the success of BNN, search an appropriate architecture of the neural networks is an important task, and various algorithms to find good sparse neural networks have been proposed. In this paper, we propose a new node-sparse BNN model which has good theoretical properties and is computationally feasible. We prove that the posterior concentration rate to the true model is near minimax optimal and adaptive to the smoothness of the true model. In particular the adaptiveness is the first of its kind for node-sparse BNNs. In addition, we develop a novel MCMC algorithm which makes the Bayesian inference of the node-sparse BNN model feasible in practice.
Files in This Item:
There are no files associated with this item.
Appears in Collections:


Item View & Download Count

  • mendeley

Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.