conftrace_

2015 AISTATS AISTATS 2015

Scalable Variational Gaussian Process Classification

Abstract

Gaussian process classification is a popular method with a number of appealing properties. We show how to scale the model within a variational inducing point framework, out-performing the state of the art on benchmark datasets. Importantly, the variational formulation an be exploited to allow classification in problems with millions of data points, as we demonstrate in experiments.

🐣 Hot Topic Early Bird - posterior approximation

Authors

James Hensman, Alexander Matthews, Zoubin Ghahramani

Topics

Machine Learning > Core Methods > Classification Machine Learning > Optimization & Theory > Bayesian Inference Deep Learning > Models > Variational Inference Machine Learning > Bayesian & Probabilistic > Variational Inference Machine Learning > Bayesian & Probabilistic > Gaussian Processes

Keywords

stochastic optimization variational inference gaussian process classification posterior approximation variational gaussian process scalable inference inducing point variational inducing point

More from AISTATS 2015

All AISTATS 2015 papers →

Preserving Privacy of Continuous High-dimensional Data with Minimax Filters

A Consistent Method for Graph Based Anomaly Localization

Metric recovery from directed unweighted graphs

Stochastic Structured Variational Inference

Reliable and Scalable Variational Inference for the Hierarchical Dirichlet Process

Cross-domain recommendation without shared users or items by sharing latent vector distributions