Scalable Gaussian Process Variational Autoencoders

2020/10/26 by Jazbec, Metod, Matthew Ashman, Vincent Fortuin +6 · 2 citations
Computer Science · Physics and Astronomy · #FOS: Computer and information sciences #Gaussian Processes and Bayesian Inference #Generative Adversarial Networks and Image Synthesis #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Model Reduction and Neural Networks

paper · pdf · doi:10.48550/arxiv.2010.13472

openalex publication_date 2020/10/26 · openalex created_date 2020/10/29 · openalex updated_date 2026/07/28

Abstract

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 this regard, but is still inhibited by the intrinsic complexity of exact GP inference. We improve the scalability of these methods through principled sparse inference approaches. We propose a new scalable GP-VAE model that outperforms existing approaches in terms of runtime and memory footprint, is easy to implement, and allows for joint end-to-end optimization of all components.

Citations

• Stochastic Backpropagation and Approximate Inference in Deep Generative\n Models
• Auto-Encoding Variational Bayes
• Gradient-based learning applied to document recognition
• Composing graphical models with neural networks for structured representations and fast inference
• Generative Models of Visually Grounded Imagination
• Variational Inference for Gaussian Process Models with Linear Complexity
• Inference Suboptimality in Variational Autoencoders
• EDDI: Efficient Dynamic Discovery of High-Value Information with Partial\n VAE
• Rates of Convergence for Sparse Variational Gaussian Process Regression
• Spatio-Temporal Data Mining
• Quadruply Stochastic Gaussian Processes

Cited by

• When Bayesian Tensor Completion Meets Multioutput Gaussian Processes: Functional Universality and Rank Learning
• Latent-Autoregressive GP-VAE Language Model

Related

• Sparse Gaussian Process Variational Autoencoders
• Neighbour-Driven Gaussian Process Variational Autoencoders for Scalable Structured Latent Modelling
• Factorized Gaussian Process Variational Autoencoders
• Gaussian Process Prior Variational Autoencoders
• Variational Auto-encoded Deep Gaussian Processes