Nested Variational Compression in Deep Gaussian Processes

2014/12/03 by James Hensman, Hensman, James, Neil D. Lawrence +1 · 1 citation
Computer Science · Engineering · Mathematics · #Applied mathematics #Compression (physics) #Computer science #Control Systems and Identification #FOS: Computer and information sciences #Gaussian #Gaussian Processes and Bayesian Inference #Geology #Machine Learning (stat.ML) #Mathematics #Physics #Statistical physics #Target Tracking and Data Fusion in Sensor Networks #Thermodynamics #stat.ML

paper · pdf · doi:10.48550/arxiv.1412.1370

arxiv created 2014/12/03 · openalex publication_date 2014/12/03 · arxiv updated 2014/12/04 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Deep Gaussian processes provide a flexible approach to probabilistic modelling of data using either supervised or unsupervised learning. For tractable inference approximations to the marginal likelihood of the model must be made. The original approach to approximate inference in these models used variational compression to allow for approximate variational marginalization of the hidden variables leading to a lower bound on the marginal likelihood of the model [Damianou and Lawrence, 2013]. In this paper we extend this idea with a nested variational compression. The resulting lower bound on the likelihood can be easily parallelized or adapted for stochastic variational inference.

Citations

• Distributed Variational Inference in Sparse Gaussian Process Regression and Latent Variable Models
• Stochastic Variational Inference

Cited by

• Sparse Techniques for Regression in Deep Gaussian Processes

Related

• Variational Auto-encoded Deep Gaussian Processes
• The Variational Gaussian Process
• Beyond the Mean-Field: Structured Deep Gaussian Processes Improve the Predictive Uncertainties
• Sparse Orthogonal Variational Inference for Gaussian Processes
• Doubly Stochastic Variational Inference for Deep Gaussian Processes