paper-with-me

Papers

Exact posterior distributions of wide Bayesian neural networks

2020-06-18 · Jiri Hron, Yasaman Bahri, Roman Novak, Jeffrey Pennington, Jascha Sohl-Dickstein

Recent work has shown that the prior over functions induced by a deep Bayesian neural network (BNN) behaves as a Gaussian process (GP) as the width of all layers becomes large. However, many BNN applications are concerned with the BNN function space posterior. While some empirical evidence of the posterior convergence was provided in the original works of Neal (1996) and Matthews et al. (2018), it is limited to small datasets or architectures due to the notorious difficulty of obtaining and verifying exactness of BNN posterior approximations. We provide the missing theoretical proof that the exact BNN posterior converges (weakly) to the one induced by the GP limit of the prior. For empirical validation, we show how to generate exact samples from a finite BNN on a small dataset via rejection sampling.

📄 PDF Abstract BibTeX arXiv:2006.10541

Code (1)

google/wide_bnn_sampling jax

Methods 이 논문이 사용한 방법론

Gaussian Process Gaussian Processes are non-parametric models for approximating functions. They rely upon a measure of similarity between points (the kernel function) to predict the value for…

Similar Papers 제목 키워드 기반

Boosting Variational Inference

2016-11-17 · Fangjian Guo, Xiangyu Wang, Kai Fan, Tamara Broderick 외

Variational inference (VI) provides fast approximations of a Bayesian posterior in part because it formulates posterior approximation as an optimization problem: to find the closest distribution to the exact posterior ov…

Variational Inference

Challenges in Markov chain Monte Carlo for Bayesian neural networks

2019-10-15 · Theodore Papamarkou, Jacob Hinkle, M. Todd Young, David Womble

Markov chain Monte Carlo (MCMC) methods have not been broadly adopted in Bayesian neural networks (BNNs). This paper initially reviews the main challenges in sampling from the parameter posterior of a neural network via …

Bayesian Inferencevalid

Discovering Inductive Bias with Gibbs Priors: A Diagnostic Tool for Approximate Bayesian Inference

2022-03-07 · Luca Rendsburg, Agustinus Kristiadi, Philipp Hennig, Ulrike Von Luxburg

Full Bayesian posteriors are rarely analytically tractable, which is why real-world Bayesian inference heavily relies on approximate techniques. Approximations generally differ from the true posterior and require diagnos…

Bayesian InferenceDiagnosticInductive Bias

Scalable Nonparametric Sampling from Multimodal Posteriors with the Posterior Bootstrap

2019-02-08 · Edwin Fong, Simon Lyddon, Chris Holmes

Increasingly complex datasets pose a number of challenges for Bayesian inference. Conventional posterior sampling based on Markov chain Monte Carlo can be too computationally intensive, is serial in nature and mixes poor…

Bayesian Inferenceregression

Spectral Bayesian Regression on the Sphere

2026-01-28 · Claudio Durastanti arxiv

We develop a fully intrinsic Bayesian framework for nonparametric regression on the unit sphere based on isotropic Gaussian field priors and the harmonic structure induced by the Laplace-Beltrami operator. Under uniform …