Timezone: »

 
Poster
Dual Parameterization of Sparse Variational Gaussian Processes
Vincent ADAM · Paul Chang · Mohammad Emtiyaz Khan · Arno Solin

Fri Dec 10 08:30 AM -- 10:00 AM (PST) @
in Poster Session 8 »

Sparse variational Gaussian process (SVGP) methods are a common choice for non-conjugate Gaussian process inference because of their computational benefits. In this paper, we improve their computational efficiency by using a dual parameterization where each data example is assigned dual parameters, similarly to site parameters used in expectation propagation. Our dual parameterization speeds-up inference using natural gradient descent, and provides a tighter evidence lower bound for hyperparameter learning. The approach has the same memory cost as the current SVGP methods, but it is faster and more accurate.

Keywords: Optimization · Generative Model · Kernel Methods

Author Information

Vincent ADAM (UCL)

PhD in computational neuroscience and machine learning at the Gatsby Unit

Paul Chang (Aalto University)

A machine learning researcher working in the Arno Solin group at Aalto University. Looking at probabilistic modelling specifically Gaussian Processes and methods to speed up inference.

Mohammad Emtiyaz Khan (RIKEN)

Emtiyaz Khan (also known as Emti) is a team leader at the RIKEN center for Advanced Intelligence Project (AIP) in Tokyo where he leads the Approximate Bayesian Inference Team. He is also a visiting professor at the Tokyo University of Agriculture and Technology (TUAT). Previously, he was a postdoc and then a scientist at Ecole Polytechnique Fédérale de Lausanne (EPFL), where he also taught two large machine learning courses and received a teaching award. He finished his PhD in machine learning from University of British Columbia in 2012. The main goal of Emti’s research is to understand the principles of learning from data and use them to develop algorithms that can learn like living beings. For the past 10 years, his work has focused on developing Bayesian methods that could lead to such fundamental principles. The approximate Bayesian inference team now continues to use these principles, as well as derive new ones, to solve real-world problems.

Arno Solin (Aalto University)

More from the Same Authors