Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes

Bridging the Gap between Variational Inference and Stochastic Gradient MCMC in Function Space

ICLR 2025 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Variational Bayesian deep learning

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Bridges functional variational inference and functional stochastic gradient MCMC for Bayesian neural networks by working in function space.

Problem

Parameter-space posterior inference for Bayesian neural networks suffers from hard-to-specify priors, pathologies in deep models, and intractable multi-modal posteriors.

Approach

Connects functional variational inference and functional MCMC (stochastic gradient MCMC in function space) to bridge the gap between the two function-space Bayesian inference schemes.

Experimental setup

Builds on: functional variational inference functional MCMC

Closest papers by meaning

• Model-Informed Flows for Bayesian Inference (NeurIPS 2025 · similarity 0.88)
• VIKING: Deep variational inference with stochastic projections (NeurIPS 2025 · similarity 0.88)
• Functional Gradient Flows for Constrained Sampling (NeurIPS 2024 · similarity 0.88)
• Generalized Variational Inference via Optimal Transport (AAAI 2024 · similarity 0.87)
• Kernel Semi-Implicit Variational Inference (ICML 2024 · similarity 0.87)
• Variational Inference with Mixtures of Isotropic Gaussians (NeurIPS 2025 · similarity 0.87)