A Tutorial on Sparse Gaussian Processes and Variational Inference

Abstract

Gaussian processes (GPs) provide a framework for Bayesian inference that can offer principled uncertainty estimates for a large range of problems. For example, if we consider regression problems with Gaussian likelihoods, a GP model enjoys a posterior in closed form. However, identifying the posterior GP scales cubically with the number of training examples and requires to store all examples in memory. In order to overcome these obstacles, sparse GPs have been proposed that approximate the true posterior GP with pseudo-training examples. Importantly, the number of pseudo-training examples is user-defined and enables control over computational and memory complexity. In the general case, sparse GPs do not enjoy closed-form solutions and one has to resort to approximate inference. In this context, a convenient choice for approximate inference is variational inference (VI), where the problem of Bayesian inference is cast as an optimization problem -- namely, to maximize a lower bound of the log marginal likelihood. This paves the way for a powerful and versatile framework, where pseudo-training examples are treated as optimization arguments of the approximate posterior that are jointly identified together with hyperparameters of the generative model (i.e. prior and likelihood). The framework can naturally handle a wide scope of supervised learning problems, ranging from regression with heteroscedastic and non-Gaussian likelihoods to classification problems with discrete labels, but also problems with multidimensional labels. The purpose of this tutorial is to provide access to the basic matter for readers without prior knowledge in both GPs and VI. A proper exposition to the subject enables also access to more recent advances (like importance-weighted VI as well as interdomain, multioutput and deep GPs) that can serve as an inspiration for new research ideas.

References in corpus (12)

• Semi-Supervised Learning with Deep Generative Models
• Weight Uncertainty in Neural Networks
• Scalable Variational Gaussian Process Classification
• Benchmarking Model-Based Reinforcement Learning
• A unified view of entropy-regularized Markov decision processes
• Exploring Model-based Planning with Policy Networks
• MCMC for Variationally Sparse Gaussian Processes
• Deep Gaussian Processes with Importance-Weighted Variational Inference
• Sparse Gaussian Processes with Spherical Harmonic Features
• Disentangled Skill Embeddings for Reinforcement Learning
• Variational Orthogonal Features
• Doubly Sparse Variational Gaussian Processes

Cited by in corpus (7)

• Nonnegative spatial factorization
• GPflux: A Library for Deep Gaussian Processes
• Sparse Uncertainty Representation in Deep Learning with Inducing Weights
• Hybrid Bayesian Neural Networks with Functional Probabilistic Layers
• Deep Neural Networks as Point Estimates for Deep Gaussian Processes
• Bellman: A Toolbox for Model-Based Reinforcement Learning in TensorFlow
• Gaussian Processes on Hypergraphs