Sparse Gaussian Process Variational Autoencoders

2020-10-20 · Matthew Ashman, Jonathan So, Will Tebbutt, Vincent Fortuin, Michael Pearce, Richard E. Turner

Large, multi-dimensional spatio-temporal datasets are omnipresent in modern science and engineering. An effective framework for handling such data are Gaussian process deep generative models (GP-DGMs), which employ GP priors over the latent variables of DGMs. Existing approaches for performing inference in GP-DGMs do not support sparse GP approximations based on inducing points, which are essential for the computational efficiency of GPs, nor do they handle missing data -- a natural occurrence in many spatio-temporal datasets -- in a principled manner. We address these shortcomings with the development of the sparse Gaussian process variational autoencoder (SGP-VAE), characterised by the use of partial inference networks for parameterising sparse GP approximations. Leveraging the benefits of amortised variational inference, the SGP-VAE enables inference in multi-output sparse GPs on previously unobserved data with no additional training. The SGP-VAE is evaluated in a variety of experiments where it outperforms alternative approaches including multi-output GPs and structured VAEs.

📄 PDF Abstract BibTeX arXiv:2010.10177

Code (1)

MattAshman/sgpvae 공식 구현 pytorch

Tasks

Computational EfficiencyVariational Inference

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…

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…

Solana Customer Service Number +1-833-534-1729 설명 없음

Fully Bayesian Autoencoders with Latent Sparse Gaussian Processes

2023-02-09 · Ba-Hien Tran, Babak Shahbaba, Stephan Mandt, Maurizio Filippone

Autoencoders and their variants are among the most widely used models in representation learning and generative modeling. However, autoencoder-based models usually assume that the learned representations are i.i.d. and f…

Gaussian Processes Representation Learning

Scalable Gaussian Process Variational Autoencoders

2020-10-26 · Metod Jazbec, Matthew Ashman, Vincent Fortuin, Michael Pearce 외

Conventional variational autoencoders fail in modeling correlations between data points due to their use of factorized priors. Amortized Gaussian process inference through GP-VAEs has led to significant improvements in t…

Uncertainty Quantification for Scientific Machine Learning using Sparse Variational Gaussian Process Kolmogorov-Arnold Networks (SVGP KAN)

2025-12-04 · Y. Sungtaek Ju arxiv

Kolmogorov-Arnold Networks have emerged as interpretable alternatives to traditional multi-layer perceptrons. However, standard implementations lack principled uncertainty quantification capabilities essential for many s…

Out-of-Distribution Detection Bayesian Inference

Factorized Gaussian Process Variational Autoencoders

2020-11-14 · pproximateinference AABI Symposium 2021 1 · Metod Jazbec, Michael Pearce, Vincent Fortuin

Variational autoencoders often assume isotropic Gaussian priors and mean-field posteriors, hence do not exploit structure in scenarios where we may expect similarity or consistency across latent variables. Gaussian proce…

The advantage of using Student's t-priors in variational autoencoders

2019-09-25 · Najmeh Abiri, Mattias Ohlsson

Is it optimal to use the standard Gaussian prior in variational autoencoders? With Gaussian distributions, which are not weakly informative priors, variational autoencoders struggle to reconstruct the actual data. We pro…