arXiv:2303.13930
공식 코드 · Papers with Code
Particle Mean Field Variational Bayes
원문 초록
The Mean Field Variational Bayes (MFVB) method is one of the most computationally efficient techniques for Bayesian inference. However, its use has been restricted to models with conjugate priors or those that require analytical calculations. This paper proposes a novel particle-based MFVB approach that greatly expands the applicability of the MFVB method. We establish the theoretical basis of the new method by leveraging the connection between Wasserstein gradient flows and Langevin diffusion dynamics, and demonstrate the effectiveness of this approach using Bayesian logistic regression, stochastic volatility, and deep neural networks.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Bayesian Data Sketching for Varying Coefficient Regression Models
Normalizing Flow Regression for Bayesian Inference with Offline Likelihood Evaluations
Statistical Machine Learning for Astronomy -- A Textbook
A Simple Approximate Bayesian Inference Neural Surrogate for Stochastic Petri Net Models
Active Learning for Manifold Gaussian Process Regression
Scalable Bayesian Low-Rank Adaptation of Large Language Models via Stochastic Variational Subspace Inference
토론
이 논문과 연결된 포럼 글이 아직 없습니다.