paper-with-me

홈 › Papers

Theory and computation for structured variational inference

2025-11-13 · Shunan Sheng, Bohan Wu, Bennett Zhu, Sinho Chewi, Aram-Alexandre Pooladian arxiv

Structured variational inference constitutes a core methodology in modern statistical applications. Unlike mean-field variational inference, the approximate posterior is assumed to have interdependent structure. We consider the natural setting of star-structured variational inference, where a root variable impacts all the other ones. We prove the first results for existence, uniqueness, and self-consistency of the variational approximation. In turn, we derive quantitative approximation error bounds for the variational approximation to the posterior, extending prior work from the mean-field setting to the star-structured setting. We also develop a gradient-based algorithm with provable guarantees for computing the variational approximation using ideas from optimal transport theory. We explore the implications of our results for Gaussian measures and hierarchical Bayesian models, including generalized linear models with location family priors and spike-and-slab priors with one-dimensional debiasing. As a by-product of our analysis, we develop new stability results for star-separable transport maps which might be of independent interest.

📄 PDF Abstract BibTeX arXiv:2511.09897

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Divide-and-Conquer Predictive Coding: a structured Bayesian inference algorithm

2024-08-11 · Eli Sennesh, Hao Wu, Tommaso Salvatori

Unexpected stimuli induce "error" or "surprise" signals in the brain. The theory of predictive coding promises to explain these observations in terms of Bayesian inference by suggesting that the cortex implements variati…

Bayesian InferenceVariational Inference

Extending Mean-Field Variational Inference via Entropic Regularization: Theory and Computation

2024-04-14 · Bohan Wu, David Blei

Variational inference (VI) has emerged as a popular method for approximate inference for high-dimensional Bayesian models. In this paper, we propose a novel VI method that extends the naive mean field via entropic regula…

Variational Inference

Structured Variational Inference for Coupled Gaussian Processes

2017-11-03 · Vincent Adam

Sparse variational approximations allow for principled and scalable inference in Gaussian Process (GP) models. In settings where several GPs are part of the generative model, theses GPs are a posteriori coupled. For many…

Gaussian ProcessesVariational Inference

Efficient Approximate Inference with Walsh-Hadamard Variational Inference

2019-11-29 · Simone Rossi, Sebastien Marmin, Maurizio Filippone

Variational inference offers scalable and flexible tools to tackle intractable Bayesian inference of modern statistical models like Bayesian neural networks and Gaussian processes. For largely over-parameterized models, …

Bayesian InferenceGaussian ProcessesVariational Inference

Two Methods For Wild Variational Inference

2016-11-30 · Qiang Liu, Yihao Feng

Variational inference provides a powerful tool for approximate probabilistic in- ference on complex, structured models. Typical variational inference methods, however, require to use inference networks with computational…

Variational InferenceVocal Bursts Valence Prediction