paper-with-me

홈 › Papers

PriorVAE: Encoding spatial priors with VAEs for small-area estimation

2021-10-20 · Elizaveta Semenova, Yidan Xu, Adam Howes, Theo Rashid, Samir Bhatt, Swapnil Mishra, Seth Flaxman

Gaussian processes (GPs), implemented through multivariate Gaussian distributions for a finite collection of data, are the most popular approach in small-area spatial statistical modelling. In this context they are used to encode correlation structures over space and can generalise well in interpolation tasks. Despite their flexibility, off-the-shelf GPs present serious computational challenges which limit their scalability and practical usefulness in applied settings. Here, we propose a novel, deep generative modelling approach to tackle this challenge, termed PriorVAE: for a particular spatial setting, we approximate a class of GP priors through prior sampling and subsequent fitting of a variational autoencoder (VAE). Given a trained VAE, the resultant decoder allows spatial inference to become incredibly efficient due to the low dimensional, independently distributed latent Gaussian space representation of the VAE. Once trained, inference using the VAE decoder replaces the GP within a Bayesian sampling framework. This approach provides tractable and easy-to-implement means of approximately encoding spatial priors and facilitates efficient statistical inference. We demonstrate the utility of our VAE two stage approach on Bayesian, small-area estimation tasks.

📄 PDF Abstract BibTeX arXiv:2110.10422

Code (1)

elizavetasemenova/priorvae 공식 구현 pytorch

Tasks

DecoderGaussian Processes

Methods 이 논문이 사용한 방법론

GPS Greedy Policy Search (GPS) is a simple algorithm that learns a policy for test-time data augmentation based on the predictive performance on a validation set. GPS starts with…

Similar Papers 제목 키워드 기반

DeepRV: pre-trained spatial priors for accelerated disease mapping

2025-03-27 · Jhonathan Navott, Daniel Jenson, Seth Flaxman, Elizaveta Semenova

Recently introduced prior-encoding deep generative models (e.g., PriorVAE, $\pi$VAE, and PriorCVAE) have emerged as powerful tools for scalable Bayesian inference by emulating complex stochastic processes like Gaussian p…

Bayesian InferenceDecoderGaussian ProcessesProbabilistic Programming

Deep learning and MCMC with aggVAE for shifting administrative boundaries: mapping malaria prevalence in Kenya

2023-05-31 · Elizaveta Semenova, Swapnil Mishra, Samir Bhatt, Seth Flaxman 외

Model-based disease mapping remains a fundamental policy-informing tool in the fields of public health and disease surveillance. Hierarchical Bayesian models have emerged as the state-of-the-art approach for disease mapp…

Bayesian Inference

Spatial Variational Auto-Encoding via Matrix-Variate Normal Distributions

2017-05-18 · Zhengyang Wang, Hao Yuan, Shuiwang Ji

The key idea of variational auto-encoders (VAEs) resembles that of traditional auto-encoder models in which spatial information is supposed to be explicitly encoded in the latent space. However, the latent variables in V…

PriorCVAE: scalable MCMC parameter inference with Bayesian deep generative modelling

2023-04-09 · Elizaveta Semenova, Prakhar Verma, Max Cairney-Leeming, Arno Solin 외

Recent advances have shown that GP priors, or their finite realisations, can be encoded using deep generative models such as variational autoencoders (VAEs). These learned generators can serve as drop-in replacements for…

Bayesian InferenceGaussian Processes

On Incorporating Inductive Biases into VAEs

2021-06-25 · ICLR 2022 4 · Ning Miao, Emile Mathieu, N. Siddharth, Yee Whye Teh 외

We explain why directly changing the prior can be a surprisingly ineffective mechanism for incorporating inductive biases into VAEs, and introduce a simple and effective alternative approach: Intermediary Latent Space VA…

Inductive Bias