paper-with-me

홈 › Papers

Understanding Variational Inference in Function-Space

2020-11-18 · pproximateinference AABI Symposium 2021 1 · David R. Burt, Sebastian W. Ober, Adrià Garriga-Alonso, Mark van der Wilk

Recent work has attempted to directly approximate the function-space' or predictive posterior distribution of Bayesian models, without approximating the posterior distribution over the parameters. This is appealing in e.g. Bayesian neural networks, where we only need the former, and the latter is hard to represent. In this work, we highlight some advantages and limitations of employing the Kullback-Leibler divergence in this setting. For example, we show that minimizing the KL divergence between a wide class of parametric distributions and the posterior induced by a (non-degenerate) Gaussian process prior leads to an ill-defined objective function. Then, we propose (featurized) Bayesian linear regression as a benchmark for function-space' inference methods that directly measures approximation quality. We apply this methodology to assess aspects of the objective function and inference scheme considered in Sun, Zhang, Shi, and Grosse (2018), emphasizing the quality of approximation to Bayesian inference as opposed to predictive performance.

📄 PDF Abstract BibTeX arXiv:2011.09421

Code (2)

victor-armegioiu/Learning-Bayesian-Priors tf
victor-armegioiu/Meta-Learning-Bayesian-Priors tf

Tasks

Bayesian InferenceVariational Inference

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…
Linear Regression Linear Regression is a method for modelling a relationship between a dependent variable and independent variables. These models can be fit with numerous approaches. The most…

Similar Papers 제목 키워드 기반

Rethinking Function-Space Variational Inference in Bayesian Neural Networks

2020-11-23 · pproximateinference AABI Symposium 2021 1 · Tim G. J. Rudner, Zonghao Chen, Yarin Gal

Bayesian neural networks (BNNs) define distributions over functions induced by distributions over parameters. In practice, this model specification makes it difficult to define and use meaningful prior distributions over…

Variational Inference

Generalized Variational Inference in Function Spaces: Gaussian Measures meet Bayesian Deep Learning

2022-05-12 · Veit D. Wild, Robert Hu, Dino Sejdinovic

We develop a framework for generalized variational inference in infinite-dimensional function spaces and use it to construct a method termed Gaussian Wasserstein inference (GWI). GWI leverages the Wasserstein distance be…

Gaussian ProcessesUncertainty QuantificationVariational Inference

Function-Space Variational Inference for Deep Bayesian Classification

2021-09-29 · Jihao Andreas Lin, Joe Watson, Pascal Klink, Jan Peters

Bayesian deep learning approaches assume model parameters to be latent random variables and infer posterior predictive distributions to quantify uncertainty, increase safety and trust, and prevent overconfident and unpre…

Adversarial RobustnessClassificationimage-classificationImage Classification+2

Functional Variational Inference based on Stochastic Process Generators

2021-12-01 · NeurIPS 2021 12 · Chao Ma, José Miguel Hernández-Lobato

Bayesian inference in the space of functions has been an important topic for Bayesian modeling in the past. In this paper, we propose a new solution to this problem called Functional Variational Inference (FVI). In FVI, …

Bayesian InferenceVariational Inference

Functional Bias and Tangent-Space Geometry in Variational Inference

2026-03-09 · Sean Plummer arxiv

Variational inference approximates Bayesian posterior distributions by projecting onto a tractable family of distributions. While most theoretical analyses evaluate the quality of this approximation using global divergen…