Connecting the Dots: Is Mode-Connectedness the Key to Feasible Sample-Based Inference in Bayesian Neural Networks?
This work addresses the problem of feasible inference for practitioners using Bayesian neural networks, but it appears incremental as it builds on existing ensemble methods.
The paper tackled the challenge of sample-based inference in Bayesian neural networks by showing that successful inference is possible through understanding the relationship between weight and function space, and presented a deep ensemble initialized approach with competitive performance and uncertainty quantification.
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 deep ensemble initialized approach as an effective solution with competitive performance and uncertainty quantification.