标签：What full Network Neural paper BNN performance ensembles HMC

summary

This paper investigates the foundational questions in BNN by using full-batch Hamiltonian Monte Carlo (HMC) on modern architectures. The primary goal of this paper is to construct accurate samples from the posterior to understand the properties of BNN, without considering computational requirements and practicality. After showing the effective way to employ full batch HMC on modern neural architectures, the authors find that (1) BNNs can achieve significant performance gains over standard training and deep ensembles, but less robust to domain shift; (2) a single long HMC chain can provide a comparable performance to multiple shorter chains; (3) cold posterior effect is largely an artifact of data augmentation. (4) BMA performance is robust to the choice of prior scale; (5) while cheaper alternatives such as deep ensembles and SGMCMC can provide good generalization, their predictive distributions are distinct from HMC. 

标签：What,full,Network,Neural,paper,BNN,performance,ensembles,HMC
来源： https://www.cnblogs.com/squirrel-7/p/15242421.html

本站声明： 1. iCode9 技术分享网（下文简称本站）提供的所有内容，仅供技术学习、探讨和分享；
2. 关于本站的所有留言、评论、转载及引用，纯属内容发起人的个人观点，与本站观点和立场无关；
3. 关于本站的所有言论和文字，纯属内容发起人的个人观点，与本站观点和立场无关；
4. 本站文章均是网友提供，不完全保证技术分享内容的完整性、准确性、时效性、风险性和版权归属；如您发现该文章侵犯了您的权益，可联系我们第一时间进行删除；
5. 本站为非盈利性的个人网站，所有内容不会用来进行牟利，也不会利用任何形式的广告来间接获益，纯粹是为了广大技术爱好者提供技术内容和技术思想的分享性交流网站。