Connecting the Dots: Is Mode-Connectedness the Key to Feasible Sample-Based Inference in Bayesian Neural Networks?
CoRR(2024)
摘要
A major challenge in sample-based inference (SBI) for Bayesian neural
networks is the size and structure of the networks' parameter space. Our work
shows that successful SBI is possible by embracing the characteristic
relationship between weight and function space, uncovering a systematic link
between overparameterization and the difficulty of the sampling problem.
Through extensive experiments, we establish practical guidelines for sampling
and convergence diagnosis. As a result, we present a Bayesian deep ensemble
approach as an effective solution with competitive performance and uncertainty
quantification.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要