Recyclable Gaussian Processes

10/06/2020
by   Pablo Moreno-Muñoz, et al.
6

We present a new framework for recycling independent variational approximations to Gaussian processes. The main contribution is the construction of variational ensembles given a dictionary of fitted Gaussian processes without revisiting any subset of observations. Our framework allows for regression, classification and heterogeneous tasks, i.e. mix of continuous and discrete variables over the same input domain. We exploit infinite-dimensional integral operators based on the Kullback-Leibler divergence between stochastic processes to re-combine arbitrary amounts of variational sparse approximations with different complexity, likelihood model and location of the pseudo-inputs. Extensive results illustrate the usability of our framework in large-scale distributed experiments, also compared with the exact inference models in the literature.

READ FULL TEXT
research
10/26/2021

Modular Gaussian Processes for Transfer Learning

We present a framework for transfer learning based on modular variationa...
research
05/22/2018

Variational Learning on Aggregate Outputs with Gaussian Processes

While a typical supervised learning framework assumes that the inputs an...
research
03/05/2020

Knot Selection in Sparse Gaussian Processes with a Variational Objective

Sparse, knot-based Gaussian processes have enjoyed considerable success ...
research
04/27/2015

On Sparse variational methods and the Kullback-Leibler divergence between stochastic processes

The variational framework for learning inducing variables (Titsias, 2009...
research
06/15/2016

Understanding Probabilistic Sparse Gaussian Process Approximations

Good sparse approximations are essential for practical inference in Gaus...
research
03/21/2018

Scalable Generalized Dynamic Topic Models

Dynamic topic models (DTMs) model the evolution of prevalent themes in l...
research
09/06/2017

Convolutional Gaussian Processes

We present a practical way of introducing convolutional structure into G...

Please sign up or login with your details

Forgot password? Click here to reset